Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 585 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.4733. Min Act: -0.1700
Data Index: 1927789 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.3483. Min Act: -0.1700
Data Index: 3226701 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.2858. Min Act: -0.1700
Data Index: 6601171 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.2233. Min Act: -0.1700
Data Index: 5164192 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.2233. Min Act: -0.1700
Data Index: 4294942 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.1921. Min Act: -0.1700
Data Index: 951942 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.1921. Min Act: -0.1700
Data Index: 4133256 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.1608. Min Act: -0.1700
Data Index: 8769383 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.1608. Min Act: -0.1700
Data Index: 7310306 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.1296. Min Act: -0.1700
Data Index: 469467 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0983. Min Act: -0.1700
Data Index: 4154038 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0671. Min Act: -0.1700
Data Index: 2828704 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0671. Min Act: -0.1700
Data Index: 7604778 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0671. Min Act: -0.1700
Data Index: 874092 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0358. Min Act: -0.1700
Data Index: 1285085 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0358. Min Act: -0.1700
Data Index: 178789 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0358. Min Act: -0.1700
Data Index: 2514191 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0046. Min Act: -0.1700
Data Index: 6763422 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0358. Min Act: -0.1700
Data Index: 2947489 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4733. Min Range: -7.4733
Max Act: 7.0358. Min Act: -0.1700
Data Index: 3459970 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19