Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5591 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.5233. Min Act: -0.1700
Data Index: 8263340 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.4921. Min Act: -0.1700
Data Index: 276876 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.4608. Min Act: -0.1700
Data Index: 5900590 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.4608. Min Act: -0.1700
Data Index: 1081868 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.4296. Min Act: -0.1700
Data Index: 3487440 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.4296. Min Act: -0.1700
Data Index: 5025409 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3983. Min Act: -0.1700
Data Index: 501598 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3983. Min Act: -0.1700
Data Index: 5480750 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3983. Min Act: -0.1700
Data Index: 3310093 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3983. Min Act: -0.1700
Data Index: 6112587 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3983. Min Act: -0.1700
Data Index: 7778856 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 6440253 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 4244039 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 2375341 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 6747298 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 6274705 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 2209973 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 7298117 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 2411119 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5233. Min Range: -4.5233
Max Act: 4.3671. Min Act: -0.1700
Data Index: 1814672 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19