Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2629 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3661. Min Range: -8.3661
Max Act: 8.3661. Min Act: -0.1700
Data Index: 3793323 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3661. Min Range: -8.3661
Max Act: 8.1786. Min Act: -0.1700
Data Index: 2442024 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.9598. Min Act: -0.1700
Data Index: 1893997 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.8661. Min Act: -0.1700
Data Index: 6064241 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.7411. Min Act: -0.1700
Data Index: 5954598 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.7411. Min Act: -0.1700
Data Index: 4474749 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.7098. Min Act: -0.1700
Data Index: 4184640 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.7098. Min Act: -0.1700
Data Index: 3800067 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.6786. Min Act: -0.1700
Data Index: 2647618 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.6786. Min Act: -0.1700
Data Index: 7504388 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.6786. Min Act: -0.1700
Data Index: 1581169 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.6473. Min Act: -0.1700
Data Index: 3045915 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.6161. Min Act: -0.1700
Data Index: 7791806 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.5848. Min Act: -0.1700
Data Index: 3047278 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.5536. Min Act: -0.1700
Data Index: 893059 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.5223. Min Act: -0.1700
Data Index: 925343 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.4598. Min Act: -0.1700
Data Index: 2647613 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.4911. Min Act: -0.1700
Data Index: 6608796 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.4911. Min Act: -0.1700
Data Index: 4441264 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3661. Min Range: -8.3661
Max Act: 7.4598. Min Act: -0.1700
Data Index: 51556 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19