Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7963. Min Range: -8.7963
Max Act: 8.7963. Min Act: -0.1700
Data Index: 8337547 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7963. Min Range: -8.7963
Max Act: 8.3588. Min Act: -0.1700
Data Index: 1178594 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7963. Min Range: -8.7963
Max Act: 8.1713. Min Act: -0.1700
Data Index: 1070300 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7963. Min Range: -8.7963
Max Act: 8.1088. Min Act: -0.1700
Data Index: 5115078 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7963. Min Range: -8.7963
Max Act: 8.1088. Min Act: -0.1700
Data Index: 6713480 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7963. Min Range: -8.7963
Max Act: 8.0463. Min Act: -0.1700
Data Index: 6068207 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7963. Min Range: -8.7963
Max Act: 8.0463. Min Act: -0.1700
Data Index: 2248385 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7963. Min Range: -8.7963
Max Act: 8.0463. Min Act: -0.1700
Data Index: 4353931 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.9213. Min Act: -0.1700
Data Index: 4833831 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.9213. Min Act: -0.1700
Data Index: 7999816 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.9213. Min Act: -0.1700
Data Index: 1490109 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.8588. Min Act: -0.1700
Data Index: 4272479 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.8588. Min Act: -0.1700
Data Index: 2273246 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.7963. Min Act: -0.1700
Data Index: 7154140 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.7963. Min Act: -0.1700
Data Index: 5155501 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.7963. Min Act: -0.1700
Data Index: 4948966 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.7963. Min Act: -0.1700
Data Index: 1454696 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.7963. Min Act: -0.1700
Data Index: 4927370 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.7963. Min Act: -0.1700
Data Index: 2152877 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7963. Min Range: -8.7963
Max Act: 7.7963. Min Act: -0.1700
Data Index: 3311204 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19