Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.1507. Min Act: -0.1700
Data Index: 1196316 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.1507. Min Act: -0.1700
Data Index: 1159179 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.1507. Min Act: -0.1700
Data Index: 1196315 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.1195. Min Act: -0.1700
Data Index: 6241926 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.1195. Min Act: -0.1700
Data Index: 7860600 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0570. Min Act: -0.1700
Data Index: 568621 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0570. Min Act: -0.1700
Data Index: 3784096 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0257. Min Act: -0.1700
Data Index: 1168808 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0570. Min Act: -0.1700
Data Index: 6848592 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0257. Min Act: -0.1700
Data Index: 5330703 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0257. Min Act: -0.1700
Data Index: 56172 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0257. Min Act: -0.1700
Data Index: 2457385 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1507. Min Range: -5.1507
Max Act: 4.9945. Min Act: -0.1700
Data Index: 8704213 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0257. Min Act: -0.1700
Data Index: 8806840 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1507. Min Range: -5.1507
Max Act: 5.0257. Min Act: -0.1700
Data Index: 6046899 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1507. Min Range: -5.1507
Max Act: 4.9945. Min Act: -0.1700
Data Index: 6752756 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1507. Min Range: -5.1507
Max Act: 4.9945. Min Act: -0.1700
Data Index: 1217702 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1507. Min Range: -5.1507
Max Act: 4.9945. Min Act: -0.1700
Data Index: 8255647 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1507. Min Range: -5.1507
Max Act: 4.9945. Min Act: -0.1700
Data Index: 6236138 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1507. Min Range: -5.1507
Max Act: 4.9632. Min Act: -0.1700
Data Index: 735772 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19