Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.8479. Min Act: -0.1700
Data Index: 2149592 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.8167. Min Act: -0.1700
Data Index: 6499358 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.8479. Min Act: -0.1700
Data Index: 2707757 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.7854. Min Act: -0.1700
Data Index: 1763869 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.7542. Min Act: -0.1700
Data Index: 7954242 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.7229. Min Act: -0.1700
Data Index: 3620325 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.7229. Min Act: -0.1700
Data Index: 8291799 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.7542. Min Act: -0.1700
Data Index: 2048416 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.6604. Min Act: -0.1700
Data Index: 7600518 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.6292. Min Act: -0.1700
Data Index: 560427 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.6292. Min Act: -0.1700
Data Index: 198897 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5667. Min Act: -0.1700
Data Index: 4912877 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5667. Min Act: -0.1700
Data Index: 5569238 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5354. Min Act: -0.1700
Data Index: 7954240 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5354. Min Act: -0.1700
Data Index: 6713580 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5354. Min Act: -0.1700
Data Index: 7954241 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5354. Min Act: -0.1700
Data Index: 815934 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5354. Min Act: -0.1700
Data Index: 557494 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5042. Min Act: -0.1700
Data Index: 360129 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8479. Min Range: -5.8479
Max Act: 5.5042. Min Act: -0.1700
Data Index: 7192542 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19