Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0601. Min Range: -7.0601
Max Act: 7.0601. Min Act: -0.1700
Data Index: 238720 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0601. Min Range: -7.0601
Max Act: 7.0288. Min Act: -0.1700
Data Index: 8223705 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.9976. Min Act: -0.1700
Data Index: 4336377 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.9663. Min Act: -0.1700
Data Index: 3579019 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.9663. Min Act: -0.1700
Data Index: 3029474 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.9038. Min Act: -0.1700
Data Index: 1550223 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.8101. Min Act: -0.1700
Data Index: 3373214 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.8413. Min Act: -0.1700
Data Index: 1351686 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.8101. Min Act: -0.1700
Data Index: 1268331 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.8101. Min Act: -0.1700
Data Index: 4354558 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.7788. Min Act: -0.1700
Data Index: 4461199 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.8101. Min Act: -0.1700
Data Index: 5969578 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.7476. Min Act: -0.1700
Data Index: 3416603 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.7476. Min Act: -0.1700
Data Index: 1852721 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.7476. Min Act: -0.1700
Data Index: 1766565 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.7163. Min Act: -0.1700
Data Index: 3542225 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.6851. Min Act: -0.1700
Data Index: 5871283 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.6851. Min Act: -0.1700
Data Index: 7875515 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.6851. Min Act: -0.1700
Data Index: 2548428 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.6538. Min Act: -0.1700
Data Index: 1981355 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19