Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6657. Min Act: -0.1087
Data Index: 4423556 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6657. Min Act: -0.1632
Data Index: 7931042 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6657. Min Act: -0.1166
Data Index: 1743574 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6483. Min Act: -0.1700
Data Index: 6110217 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6483. Min Act: -0.1699
Data Index: 2085967 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6309. Min Act: -0.1491
Data Index: 985311 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6221. Min Act: -0.1622
Data Index: 1254115 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6309. Min Act: -0.1475
Data Index: 5006384 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6221. Min Act: -0.1400
Data Index: 1743575 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6309. Min Act: -0.1699
Data Index: 3239353 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6134. Min Act: -0.1697
Data Index: 2728766 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6134. Min Act: -0.1631
Data Index: 3396987 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6134. Min Act: -0.1517
Data Index: 3113025 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6134. Min Act: -0.1148
Data Index: 1446293 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6221. Min Act: -0.1670
Data Index: 4552222 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.5960. Min Act: -0.1526
Data Index: 6455796 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.5960. Min Act: -0.1211
Data Index: 2467502 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.6047. Min Act: -0.1189
Data Index: 8031989 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.5872. Min Act: -0.1673
Data Index: 6508363 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6657. Min Range: -1.6657
Max Act: 1.5960. Min Act: -0.1578
Data Index: 283299 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19