Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2188 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.4514. Min Act: -0.1700
Data Index: 5918354 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.3573. Min Act: -0.1700
Data Index: 5843274 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.2788. Min Act: -0.1700
Data Index: 8797670 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.2631. Min Act: -0.1700
Data Index: 7759554 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.2631. Min Act: -0.1700
Data Index: 3687155 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.2317. Min Act: -0.1700
Data Index: 4151264 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.2474. Min Act: -0.1700
Data Index: 7125262 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.2160. Min Act: -0.1700
Data Index: 1274601 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.2003. Min Act: -0.1700
Data Index: 4650333 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.1058. Min Act: -0.1700
Data Index: 4650332 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.1216. Min Act: -0.1700
Data Index: 4855212 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.1216. Min Act: -0.1700
Data Index: 8496259 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.1216. Min Act: -0.1700
Data Index: 4019604 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.1058. Min Act: -0.1700
Data Index: 8552225 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.0901. Min Act: -0.1700
Data Index: 5121730 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.0901. Min Act: -0.1700
Data Index: 6905744 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.0585. Min Act: -0.1700
Data Index: 3372771 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.0585. Min Act: -0.1700
Data Index: 413376 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.0427. Min Act: -0.1700
Data Index: 163978 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4514. Min Range: -3.4514
Max Act: 3.0269. Min Act: -0.1700
Data Index: 5821832 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19