Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5388 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.5147. Min Act: -0.1700
Data Index: 136608 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.4661. Min Act: -0.1700
Data Index: 7552739 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.4335. Min Act: -0.1700
Data Index: 136613 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.4335. Min Act: -0.1700
Data Index: 8322572 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.4173. Min Act: -0.1700
Data Index: 498080 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.4173. Min Act: -0.1700
Data Index: 1343890 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.4173. Min Act: -0.1700
Data Index: 136607 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.4010. Min Act: -0.1700
Data Index: 3167079 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3846. Min Act: -0.1700
Data Index: 136612 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3519. Min Act: -0.1700
Data Index: 4385326 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3519. Min Act: -0.1700
Data Index: 5966074 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3519. Min Act: -0.1700
Data Index: 136611 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3355. Min Act: -0.1700
Data Index: 7773416 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3519. Min Act: -0.1700
Data Index: 8538033 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3355. Min Act: -0.1700
Data Index: 6494513 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3519. Min Act: -0.1700
Data Index: 3700852 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3191. Min Act: -0.1700
Data Index: 3167081 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3027. Min Act: -0.1700
Data Index: 2665490 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3191. Min Act: -0.1700
Data Index: 1693857 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5147. Min Range: -2.5147
Max Act: 2.3027. Min Act: -0.1700
Data Index: 2663310 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19