Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.8036. Min Act: -0.1700
Data Index: 2735990 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.5224. Min Act: -0.1700
Data Index: 683411 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.4286. Min Act: -0.1700
Data Index: 6748227 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.3349. Min Act: -0.1700
Data Index: 7070790 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.3349. Min Act: -0.1700
Data Index: 3012909 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.3036. Min Act: -0.1700
Data Index: 633418 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.2724. Min Act: -0.1700
Data Index: 2988676 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.2411. Min Act: -0.1700
Data Index: 1044734 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.2411. Min Act: -0.1700
Data Index: 3522789 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.1786. Min Act: -0.1700
Data Index: 1076269 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.1786. Min Act: -0.1700
Data Index: 8659945 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.1474. Min Act: -0.1700
Data Index: 836287 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.1474. Min Act: -0.1700
Data Index: 7093040 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.1474. Min Act: -0.1700
Data Index: 5105894 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.0849. Min Act: -0.1700
Data Index: 1730504 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.0849. Min Act: -0.1700
Data Index: 1152680 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.0536. Min Act: -0.1700
Data Index: 4390182 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.0536. Min Act: -0.1700
Data Index: 4802765 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.0536. Min Act: -0.1700
Data Index: 5393719 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8036. Min Range: -6.8036
Max Act: 6.0224. Min Act: -0.1700
Data Index: 8550764 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19