Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1811 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0975. Min Range: -2.0975
Max Act: 2.0975. Min Act: -0.1700
Data Index: 883541 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0975. Min Range: -2.0975
Max Act: 2.0639. Min Act: -0.1700
Data Index: 8239533 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0975. Min Range: -2.0975
Max Act: 2.0471. Min Act: -0.1700
Data Index: 4728698 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0975. Min Range: -2.0975
Max Act: 2.0471. Min Act: -0.1700
Data Index: 8753629 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0975. Min Range: -2.0975
Max Act: 2.0302. Min Act: -0.1700
Data Index: 8768982 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0975. Min Range: -2.0975
Max Act: 2.0302. Min Act: -0.1700
Data Index: 743008 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9965. Min Act: -0.1700
Data Index: 3357064 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9965. Min Act: -0.1700
Data Index: 7533418 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9965. Min Act: -0.1700
Data Index: 3866370 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9796. Min Act: -0.1700
Data Index: 5878309 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9965. Min Act: -0.1700
Data Index: 1319994 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9796. Min Act: -0.1700
Data Index: 2820873 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9796. Min Act: -0.1700
Data Index: 4931182 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9796. Min Act: -0.1700
Data Index: 2720927 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9796. Min Act: -0.1700
Data Index: 1017779 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9796. Min Act: -0.1700
Data Index: 5007762 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9796. Min Act: -0.1699
Data Index: 6506516 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9626. Min Act: -0.1700
Data Index: 1320244 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9796. Min Act: -0.1700
Data Index: 1320243 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0975. Min Range: -2.0975
Max Act: 1.9457. Min Act: -0.1700
Data Index: 786195 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19