Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.3302. Min Act: -0.1700
Data Index: 7409672 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.2313. Min Act: -0.1700
Data Index: 446774 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.2148. Min Act: -0.1700
Data Index: 5643521 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.2313. Min Act: -0.1700
Data Index: 7850545 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.2148. Min Act: -0.1700
Data Index: 922765 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.2148. Min Act: -0.1700
Data Index: 2781050 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.2148. Min Act: -0.1700
Data Index: 1868124 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.2148. Min Act: -0.1700
Data Index: 3004682 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1982. Min Act: -0.1700
Data Index: 8311554 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1982. Min Act: -0.1700
Data Index: 1084535 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.2148. Min Act: -0.1700
Data Index: 4303728 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1982. Min Act: -0.1700
Data Index: 2912709 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1816. Min Act: -0.1700
Data Index: 4586158 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1816. Min Act: -0.1700
Data Index: 7952760 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1816. Min Act: -0.1700
Data Index: 2879843 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1650. Min Act: -0.1700
Data Index: 7432265 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1650. Min Act: -0.1700
Data Index: 5037790 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1483. Min Act: -0.1700
Data Index: 5089219 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1650. Min Act: -0.1700
Data Index: 5905332 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3302. Min Range: -2.3302
Max Act: 2.1650. Min Act: -0.1700
Data Index: 1976197 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19