Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.6312. Min Act: -0.1700
Data Index: 7222325 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.6312. Min Act: -0.1700
Data Index: 8803763 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.5687. Min Act: -0.1700
Data Index: 5457682 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.5374. Min Act: -0.1700
Data Index: 6129195 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.5062. Min Act: -0.1700
Data Index: 8470836 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.4749. Min Act: -0.1700
Data Index: 3634158 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.4749. Min Act: -0.1700
Data Index: 3588852 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.4437. Min Act: -0.1700
Data Index: 4947886 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.4437. Min Act: -0.1700
Data Index: 6785817 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3812. Min Act: -0.1700
Data Index: 5002564 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3812. Min Act: -0.1700
Data Index: 3032060 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3812. Min Act: -0.1700
Data Index: 3347881 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3499. Min Act: -0.1700
Data Index: 5731971 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3499. Min Act: -0.1700
Data Index: 412522 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3499. Min Act: -0.1700
Data Index: 427473 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3187. Min Act: -0.1700
Data Index: 4998946 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3187. Min Act: -0.1700
Data Index: 1947702 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.2874. Min Act: -0.1700
Data Index: 7263047 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.3187. Min Act: -0.1700
Data Index: 3401146 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6312. Min Range: -7.6312
Max Act: 7.2562. Min Act: -0.1700
Data Index: 4503957 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19