Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3694. Min Range: -6.3694
Max Act: 6.3694. Min Act: -0.1700
Data Index: 3973937 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3694. Min Range: -6.3694
Max Act: 6.2132. Min Act: -0.1700
Data Index: 3354756 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3694. Min Range: -6.3694
Max Act: 6.0882. Min Act: -0.1700
Data Index: 8262074 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3694. Min Range: -6.3694
Max Act: 6.0569. Min Act: -0.1700
Data Index: 3871539 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3694. Min Range: -6.3694
Max Act: 6.0257. Min Act: -0.1700
Data Index: 5705245 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3694. Min Range: -6.3694
Max Act: 6.0257. Min Act: -0.1700
Data Index: 622837 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9944. Min Act: -0.1700
Data Index: 3718704 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9944. Min Act: -0.1700
Data Index: 7705998 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9944. Min Act: -0.1700
Data Index: 6310081 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9632. Min Act: -0.1700
Data Index: 271706 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9632. Min Act: -0.1700
Data Index: 8750534 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9319. Min Act: -0.1700
Data Index: 998618 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9319. Min Act: -0.1700
Data Index: 965736 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9632. Min Act: -0.1700
Data Index: 1876720 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9007. Min Act: -0.1700
Data Index: 6607525 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9007. Min Act: -0.1700
Data Index: 8688950 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9319. Min Act: -0.1700
Data Index: 8195146 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.9007. Min Act: -0.1700
Data Index: 5853110 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.8694. Min Act: -0.1700
Data Index: 4141560 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3694. Min Range: -6.3694
Max Act: 5.8694. Min Act: -0.1700
Data Index: 2141903 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19