Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3647 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.1154. Min Act: -0.1700
Data Index: 7339638 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.0986. Min Act: -0.1700
Data Index: 5496630 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.0483. Min Act: -0.1700
Data Index: 3254394 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.0651. Min Act: -0.1700
Data Index: 3536818 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.0314. Min Act: -0.1700
Data Index: 256788 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.0314. Min Act: -0.1700
Data Index: 3176169 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.0146. Min Act: -0.1700
Data Index: 6966074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.0146. Min Act: -0.1700
Data Index: 1963214 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1154. Min Range: -2.1154
Max Act: 2.0314. Min Act: -0.1700
Data Index: 8180399 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9977. Min Act: -0.1700
Data Index: 8402534 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9977. Min Act: -0.1700
Data Index: 1113470 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9808. Min Act: -0.1700
Data Index: 6647252 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9808. Min Act: -0.1700
Data Index: 1671109 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9808. Min Act: -0.1700
Data Index: 2966227 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9469. Min Act: -0.1700
Data Index: 643716 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9638. Min Act: -0.1700
Data Index: 2571761 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9638. Min Act: -0.1700
Data Index: 4749792 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9638. Min Act: -0.1700
Data Index: 4804259 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9638. Min Act: -0.1700
Data Index: 7414276 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1154. Min Range: -2.1154
Max Act: 1.9638. Min Act: -0.1699
Data Index: 2396724 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19