Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.7755. Min Act: -0.1700
Data Index: 2060440 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.4317. Min Act: -0.1700
Data Index: 3662555 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.4630. Min Act: -0.1700
Data Index: 5497841 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.4005. Min Act: -0.1700
Data Index: 1489866 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.3692. Min Act: -0.1700
Data Index: 3662556 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.4005. Min Act: -0.1700
Data Index: 3662552 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.3692. Min Act: -0.1700
Data Index: 3662554 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.3692. Min Act: -0.1700
Data Index: 3662551 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.3380. Min Act: -0.1700
Data Index: 1161190 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.3067. Min Act: -0.1700
Data Index: 3662553 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.3067. Min Act: -0.1700
Data Index: 4903000 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.3067. Min Act: -0.1698
Data Index: 1521662 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.2755. Min Act: -0.1700
Data Index: 25790 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.2755. Min Act: -0.1700
Data Index: 3662550 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.2755. Min Act: -0.1693
Data Index: 3099393 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.2755. Min Act: -0.1698
Data Index: 1489864 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.2755. Min Act: -0.1700
Data Index: 1983287 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.2442. Min Act: -0.1700
Data Index: 4603034 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.2442. Min Act: -0.1700
Data Index: 163374 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7755. Min Range: -6.7755
Max Act: 6.2755. Min Act: -0.1699
Data Index: 3420973 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19