Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0210. Min Range: -7.0210
Max Act: 7.0210. Min Act: -0.1700
Data Index: 3321623 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.9585. Min Act: -0.1699
Data Index: 8200720 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.9585. Min Act: -0.1700
Data Index: 2166179 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.9585. Min Act: -0.1700
Data Index: 6272510 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.8960. Min Act: -0.1700
Data Index: 4031573 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.8335. Min Act: -0.1700
Data Index: 6925570 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.8022. Min Act: -0.1700
Data Index: 5007303 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.7710. Min Act: -0.1700
Data Index: 7411190 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.7710. Min Act: -0.1700
Data Index: 1485524 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.7397. Min Act: -0.1700
Data Index: 6323828 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.7710. Min Act: -0.1700
Data Index: 6963651 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.7397. Min Act: -0.1700
Data Index: 3041707 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.7397. Min Act: -0.1700
Data Index: 8151632 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.7085. Min Act: -0.1700
Data Index: 4892635 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.6772. Min Act: -0.1700
Data Index: 4638215 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.6772. Min Act: -0.1700
Data Index: 7557386 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.6772. Min Act: -0.1700
Data Index: 1097188 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.6460. Min Act: -0.1700
Data Index: 7928389 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.6460. Min Act: -0.1700
Data Index: 7761833 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0210. Min Range: -7.0210
Max Act: 6.6147. Min Act: -0.1700
Data Index: 1277655 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19