Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.9310. Min Act: -0.1700
Data Index: 5383267 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.7435. Min Act: -0.1700
Data Index: 6967150 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.7435. Min Act: -0.1700
Data Index: 2131618 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6810. Min Act: -0.1700
Data Index: 2141678 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6497. Min Act: -0.1700
Data Index: 1681613 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6497. Min Act: -0.1700
Data Index: 769098 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6497. Min Act: -0.1700
Data Index: 4307989 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 3193732 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6185. Min Act: -0.1700
Data Index: 8118750 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5872. Min Act: -0.1700
Data Index: 5215948 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 2846892 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 7646846 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 6414878 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5247. Min Act: -0.1700
Data Index: 6434211 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 3960622 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5247. Min Act: -0.1700
Data Index: 4209095 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5247. Min Act: -0.1700
Data Index: 2878049 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.4935. Min Act: -0.1700
Data Index: 6592818 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.4622. Min Act: -0.1700
Data Index: 2995812 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.4935. Min Act: -0.1700
Data Index: 592841 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19