Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5212 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0237. Min Range: -10.0237
Max Act: 10.0237. Min Act: -0.1700
Data Index: 3246087 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.7112. Min Act: -0.1700
Data Index: 2236215 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.7112. Min Act: -0.1700
Data Index: 3060951 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.7112. Min Act: -0.1700
Data Index: 6217680 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.7112. Min Act: -0.1700
Data Index: 453032 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.6487. Min Act: -0.1700
Data Index: 4147868 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5862. Min Act: -0.1700
Data Index: 3235325 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5862. Min Act: -0.1700
Data Index: 262281 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5862. Min Act: -0.1700
Data Index: 3663899 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5237. Min Act: -0.1700
Data Index: 100097 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5237. Min Act: -0.1700
Data Index: 84715 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5237. Min Act: -0.1700
Data Index: 7256916 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5862. Min Act: -0.1700
Data Index: 2452519 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5237. Min Act: -0.1700
Data Index: 5461029 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5237. Min Act: -0.1700
Data Index: 90668 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5237. Min Act: -0.1700
Data Index: 1269756 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.5237. Min Act: -0.1700
Data Index: 869131 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.4612. Min Act: -0.1700
Data Index: 1784383 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.4612. Min Act: -0.1700
Data Index: 6519660 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0237. Min Range: -10.0237
Max Act: 9.3987. Min Act: -0.1700
Data Index: 3134751 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19