Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.8945. Min Act: -0.1700
Data Index: 6306009 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.8320. Min Act: -0.1700
Data Index: 1863356 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.7695. Min Act: -0.1700
Data Index: 4206336 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.6445. Min Act: -0.1700
Data Index: 6306010 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.6445. Min Act: -0.1700
Data Index: 1863355 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.5820. Min Act: -0.1700
Data Index: 4192168 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.5820. Min Act: -0.1700
Data Index: 4561756 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.5195. Min Act: -0.1700
Data Index: 1113951 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.5195. Min Act: -0.1700
Data Index: 8690510 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.4570. Min Act: -0.1700
Data Index: 7601117 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.4570. Min Act: -0.1700
Data Index: 2648496 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.4570. Min Act: -0.1700
Data Index: 1155898 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.3945. Min Act: -0.1700
Data Index: 8828755 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.3945. Min Act: -0.1700
Data Index: 5189684 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.3945. Min Act: -0.1700
Data Index: 5268982 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.3945. Min Act: -0.1700
Data Index: 7601119 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.3320. Min Act: -0.1700
Data Index: 6906222 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.3320. Min Act: -0.1700
Data Index: 3472040 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.2695. Min Act: -0.1700
Data Index: 3766571 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8945. Min Range: -8.8945
Max Act: 8.2695. Min Act: -0.1700
Data Index: 2648500 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19