Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5096 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2879. Min Range: -6.2879
Max Act: 6.2879. Min Act: -0.1259
Data Index: 7567872 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2879. Min Range: -6.2879
Max Act: 6.1004. Min Act: -0.1700
Data Index: 1286944 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.9129. Min Act: -0.1685
Data Index: 7422327 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.9129. Min Act: -0.1697
Data Index: 5621260 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.8816. Min Act: -0.1697
Data Index: 373204 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.8191. Min Act: -0.1700
Data Index: 5434594 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.6629. Min Act: -0.1695
Data Index: 5185146 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.6316. Min Act: -0.1700
Data Index: 1493327 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.6316. Min Act: -0.1700
Data Index: 3238907 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.6316. Min Act: -0.1698
Data Index: 1736161 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.6316. Min Act: -0.1700
Data Index: 180134 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.5691. Min Act: -0.1700
Data Index: 3628351 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.5691. Min Act: -0.1699
Data Index: 1286942 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.5379. Min Act: -0.1700
Data Index: 8288660 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.5379. Min Act: -0.1691
Data Index: 4559851 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.5066. Min Act: -0.1699
Data Index: 3557217 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.5066. Min Act: -0.1700
Data Index: 173396 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.5066. Min Act: -0.1699
Data Index: 6611526 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.4754. Min Act: -0.1700
Data Index: 7539352 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2879. Min Range: -6.2879
Max Act: 5.5066. Min Act: -0.1700
Data Index: 4995623 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19