Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5262 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.9584. Min Act: -0.1700
Data Index: 7196881 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.7397. Min Act: -0.1700
Data Index: 2960604 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.7084. Min Act: -0.1700
Data Index: 2246778 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.6772. Min Act: -0.1700
Data Index: 2278568 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.6147. Min Act: -0.1700
Data Index: 6482774 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4897. Min Act: -0.1700
Data Index: 377536 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4272. Min Act: -0.1700
Data Index: 6282596 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.4272. Min Act: -0.1700
Data Index: 777226 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.3959. Min Act: -0.1700
Data Index: 2930428 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.3647. Min Act: -0.1700
Data Index: 3837347 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.2709. Min Act: -0.1700
Data Index: 460745 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.3022. Min Act: -0.1700
Data Index: 992664 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.2709. Min Act: -0.1700
Data Index: 8333490 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.2397. Min Act: -0.1700
Data Index: 4299757 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.2084. Min Act: -0.1700
Data Index: 59300 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.2084. Min Act: -0.1700
Data Index: 7268872 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.2084. Min Act: -0.1700
Data Index: 7099470 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.2084. Min Act: -0.1700
Data Index: 216607 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.2084. Min Act: -0.1700
Data Index: 7926537 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9584. Min Range: -6.9584
Max Act: 6.1459. Min Act: -0.1700
Data Index: 4534379 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19