Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2215. Min Range: -8.2215
Max Act: 8.2215. Min Act: -0.1700
Data Index: 3015537 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.8152. Min Act: -0.1700
Data Index: 1770102 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.7527. Min Act: -0.1700
Data Index: 2456015 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.6277. Min Act: -0.1700
Data Index: 7844816 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.5340. Min Act: -0.1700
Data Index: 5251227 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.4402. Min Act: -0.1700
Data Index: 692135 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.4402. Min Act: -0.1700
Data Index: 2633792 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.4715. Min Act: -0.1700
Data Index: 570134 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.3777. Min Act: -0.1700
Data Index: 4815124 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.3777. Min Act: -0.1700
Data Index: 1414595 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.3465. Min Act: -0.1700
Data Index: 8513346 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.3152. Min Act: -0.1700
Data Index: 6026608 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.2215. Min Act: -0.1700
Data Index: 2927645 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.2527. Min Act: -0.1700
Data Index: 6602656 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.1277. Min Act: -0.1700
Data Index: 7969114 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.0965. Min Act: -0.1700
Data Index: 433807 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.1277. Min Act: -0.1700
Data Index: 294675 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.1590. Min Act: -0.1700
Data Index: 1476977 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.1590. Min Act: -0.1700
Data Index: 7821510 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2215. Min Range: -8.2215
Max Act: 7.0340. Min Act: -0.1700
Data Index: 8410512 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19