Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3796. Min Range: -9.3796
Max Act: 9.3796. Min Act: -0.1700
Data Index: 3152983 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3796. Min Range: -9.3796
Max Act: 9.3171. Min Act: -0.1700
Data Index: 2085247 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3796. Min Range: -9.3796
Max Act: 9.1921. Min Act: -0.1700
Data Index: 3551893 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.8796. Min Act: -0.1700
Data Index: 5819503 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.7546. Min Act: -0.1700
Data Index: 1348524 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.5046. Min Act: -0.1700
Data Index: 8404339 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.5046. Min Act: -0.1700
Data Index: 1443471 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.5046. Min Act: -0.1700
Data Index: 8557553 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.4421. Min Act: -0.1700
Data Index: 1810164 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.4421. Min Act: -0.1700
Data Index: 200902 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3796. Min Act: -0.1700
Data Index: 189271 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3796. Min Act: -0.1700
Data Index: 7852530 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3796. Min Act: -0.1700
Data Index: 8525457 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3796. Min Act: -0.1700
Data Index: 8061736 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3796. Min Act: -0.1700
Data Index: 6544351 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3796. Min Act: -0.1700
Data Index: 8656334 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3171. Min Act: -0.1700
Data Index: 1116848 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3171. Min Act: -0.1700
Data Index: 61985 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3171. Min Act: -0.1700
Data Index: 3674482 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3796. Min Range: -9.3796
Max Act: 8.3171. Min Act: -0.1700
Data Index: 3036721 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19