Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0413. Min Range: -8.0413
Max Act: 8.0413. Min Act: -0.1700
Data Index: 512826 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.9788. Min Act: -0.1700
Data Index: 5689858 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.5726. Min Act: -0.1700
Data Index: 1953514 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.5413. Min Act: -0.1700
Data Index: 1290175 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.5413. Min Act: -0.1700
Data Index: 1796221 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.3851. Min Act: -0.1700
Data Index: 3188911 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.4163. Min Act: -0.1700
Data Index: 6706473 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.4163. Min Act: -0.1700
Data Index: 5841898 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.3851. Min Act: -0.1700
Data Index: 6301610 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.3538. Min Act: -0.1700
Data Index: 6899648 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.3226. Min Act: -0.1700
Data Index: 517361 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.2601. Min Act: -0.1700
Data Index: 6829224 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.2913. Min Act: -0.1700
Data Index: 8564343 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.2601. Min Act: -0.1700
Data Index: 3417552 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.2288. Min Act: -0.1700
Data Index: 7230325 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.2601. Min Act: -0.1700
Data Index: 3031789 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.2601. Min Act: -0.1700
Data Index: 5111618 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.2288. Min Act: -0.1700
Data Index: 3635047 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.1976. Min Act: -0.1700
Data Index: 677651 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0413. Min Range: -8.0413
Max Act: 7.2288. Min Act: -0.1700
Data Index: 1473491 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19