Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4789 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5791. Min Range: -11.5791
Max Act: 11.5791. Min Act: -0.1700
Data Index: 1992587 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5791. Min Range: -11.5791
Max Act: 11.0791. Min Act: -0.1700
Data Index: 8226806 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.7666. Min Act: -0.1700
Data Index: 704197 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.7666. Min Act: -0.1700
Data Index: 6104495 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.7666. Min Act: -0.1700
Data Index: 3095003 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.7666. Min Act: -0.1700
Data Index: 5982893 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.6416. Min Act: -0.1700
Data Index: 6195339 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.6416. Min Act: -0.1700
Data Index: 901159 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.5166. Min Act: -0.1700
Data Index: 8021392 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.4541. Min Act: -0.1700
Data Index: 4731449 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.4541. Min Act: -0.1700
Data Index: 6111259 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.4541. Min Act: -0.1700
Data Index: 8493622 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.2041. Min Act: -0.1700
Data Index: 1039081 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.2666. Min Act: -0.1700
Data Index: 3145005 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.2041. Min Act: -0.1700
Data Index: 253421 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.2666. Min Act: -0.1700
Data Index: 1600671 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.2041. Min Act: -0.1700
Data Index: 1118264 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.1416. Min Act: -0.1700
Data Index: 4696334 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.1416. Min Act: -0.1700
Data Index: 2450321 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5791. Min Range: -11.5791
Max Act: 10.1416. Min Act: -0.1700
Data Index: 3945738 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19