Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 205 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.4689. Min Act: -0.1700
Data Index: 7446595 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.4689. Min Act: -0.1700
Data Index: 5078344 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.4375. Min Act: -0.1700
Data Index: 1158095 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3905. Min Act: -0.1700
Data Index: 5808217 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.4375. Min Act: -0.1700
Data Index: 101292 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3905. Min Act: -0.1700
Data Index: 3550680 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3591. Min Act: -0.1700
Data Index: 1023097 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3748. Min Act: -0.1700
Data Index: 6260291 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3905. Min Act: -0.1700
Data Index: 5633953 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3748. Min Act: -0.1700
Data Index: 3537270 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3434. Min Act: -0.1700
Data Index: 3337888 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3748. Min Act: -0.1700
Data Index: 4964524 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3905. Min Act: -0.1700
Data Index: 1152039 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.3278. Min Act: -0.1700
Data Index: 4671696 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.4375. Min Act: -0.1700
Data Index: 1596712 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.2964. Min Act: -0.1700
Data Index: 1899329 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.2807. Min Act: -0.1700
Data Index: 6902814 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.2650. Min Act: -0.1700
Data Index: 3682734 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.2964. Min Act: -0.1700
Data Index: 4378913 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4689. Min Range: -3.4689
Max Act: 3.2964. Min Act: -0.1700
Data Index: 5371600 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19