Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.8507. Min Act: -0.1700
Data Index: 5537735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.8078. Min Act: -0.1700
Data Index: 1467861 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7474. Min Act: -0.1700
Data Index: 5624019 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7215. Min Act: -0.1700
Data Index: 3701185 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7302. Min Act: -0.1700
Data Index: 2027555 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7215. Min Act: -0.1700
Data Index: 3832206 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7215. Min Act: -0.1700
Data Index: 6634977 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7128. Min Act: -0.1700
Data Index: 4144920 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7042. Min Act: -0.1700
Data Index: 6451495 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7042. Min Act: -0.1700
Data Index: 5741712 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7042. Min Act: -0.1700
Data Index: 2750208 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.7042. Min Act: -0.1700
Data Index: 2870449 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.6868. Min Act: -0.1700
Data Index: 3235632 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.6781. Min Act: -0.1700
Data Index: 285513 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.6781. Min Act: -0.1700
Data Index: 3520079 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.6955. Min Act: -0.1700
Data Index: 1953743 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.6781. Min Act: -0.1700
Data Index: 3716185 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.6868. Min Act: -0.1700
Data Index: 462909 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.6695. Min Act: -0.1700
Data Index: 8256183 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8507. Min Range: -1.8507
Max Act: 1.6781. Min Act: -0.1700
Data Index: 294192 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19