Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3699 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.7068. Min Act: -0.1700
Data Index: 1588883 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.6443. Min Act: -0.1700
Data Index: 7606982 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6286938 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.6756. Min Act: -0.1700
Data Index: 754115 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.6756. Min Act: -0.1700
Data Index: 2141425 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.6443. Min Act: -0.1700
Data Index: 2809370 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.6131. Min Act: -0.1700
Data Index: 5569579 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5818. Min Act: -0.1700
Data Index: 7732363 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5818. Min Act: -0.1700
Data Index: 15797 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5818. Min Act: -0.1700
Data Index: 941304 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5506. Min Act: -0.1700
Data Index: 437015 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5818. Min Act: -0.1700
Data Index: 1547292 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5506. Min Act: -0.1700
Data Index: 1747887 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5506. Min Act: -0.1700
Data Index: 6743741 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5506. Min Act: -0.1700
Data Index: 8400614 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5506. Min Act: -0.1700
Data Index: 5922480 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5193. Min Act: -0.1700
Data Index: 3594106 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.4881. Min Act: -0.1700
Data Index: 6796701 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5193. Min Act: -0.1700
Data Index: 3164390 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7068. Min Range: -4.7068
Max Act: 4.5193. Min Act: -0.1700
Data Index: 2192709 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19