Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1211 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.3627. Min Act: -0.1700
Data Index: 5849184 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.3627. Min Act: -0.1700
Data Index: 2845279 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.3002. Min Act: -0.1700
Data Index: 7240103 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.2689. Min Act: -0.1700
Data Index: 2822222 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.2064. Min Act: -0.1700
Data Index: 920536 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.2064. Min Act: -0.1700
Data Index: 7055828 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.1752. Min Act: -0.1700
Data Index: 4495913 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.2064. Min Act: -0.1700
Data Index: 2454445 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.1752. Min Act: -0.1700
Data Index: 2632567 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.1752. Min Act: -0.1700
Data Index: 4614470 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.1127. Min Act: -0.1700
Data Index: 1870685 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.1127. Min Act: -0.1700
Data Index: 4571000 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.1127. Min Act: -0.1700
Data Index: 2084400 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.0814. Min Act: -0.1700
Data Index: 4188475 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.0814. Min Act: -0.1700
Data Index: 8185820 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.0502. Min Act: -0.1700
Data Index: 1388940 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.0502. Min Act: -0.1700
Data Index: 5282079 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.0502. Min Act: -0.1700
Data Index: 3945426 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.0189. Min Act: -0.1700
Data Index: 794769 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3627. Min Range: -5.3627
Max Act: 5.0189. Min Act: -0.1700
Data Index: 7085916 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19