Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.5233. Min Act: -0.1700
Data Index: 6751515 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.4921. Min Act: -0.1700
Data Index: 7770501 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.3983. Min Act: -0.1700
Data Index: 1113243 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.3671. Min Act: -0.1700
Data Index: 4442789 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.3671. Min Act: -0.1700
Data Index: 8088335 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.3046. Min Act: -0.1700
Data Index: 1321694 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.2733. Min Act: -0.1700
Data Index: 3540125 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.2421. Min Act: -0.1700
Data Index: 3167334 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1796. Min Act: -0.1700
Data Index: 3594461 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1796. Min Act: -0.1700
Data Index: 4510124 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1796. Min Act: -0.1700
Data Index: 6774879 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1796. Min Act: -0.1700
Data Index: 760894 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1483. Min Act: -0.1700
Data Index: 7479995 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1171. Min Act: -0.1700
Data Index: 653792 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1483. Min Act: -0.1700
Data Index: 2173519 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1483. Min Act: -0.1700
Data Index: 1775583 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.1171. Min Act: -0.1700
Data Index: 6306720 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.0858. Min Act: -0.1700
Data Index: 6835193 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.0858. Min Act: -0.1700
Data Index: 2771780 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5233. Min Range: -7.5233
Max Act: 7.0546. Min Act: -0.1700
Data Index: 2002635 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19