Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1139 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1340. Min Range: -4.1340
Max Act: 4.1340. Min Act: -0.1700
Data Index: 8442401 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1340. Min Range: -4.1340
Max Act: 4.0715. Min Act: -0.1700
Data Index: 8233307 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9465. Min Act: -0.1700
Data Index: 1379680 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9777. Min Act: -0.1700
Data Index: 6188994 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9465. Min Act: -0.1700
Data Index: 860195 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9152. Min Act: -0.1700
Data Index: 8817574 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9152. Min Act: -0.1700
Data Index: 6188995 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9152. Min Act: -0.1700
Data Index: 3933489 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9152. Min Act: -0.1700
Data Index: 1918712 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.8839. Min Act: -0.1700
Data Index: 4441129 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.8214. Min Act: -0.1700
Data Index: 3933482 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.8527. Min Act: -0.1700
Data Index: 7871215 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.8214. Min Act: -0.1700
Data Index: 845536 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.8214. Min Act: -0.1700
Data Index: 845537 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7901. Min Act: -0.1700
Data Index: 3886218 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7745. Min Act: -0.1700
Data Index: 5063739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7745. Min Act: -0.1700
Data Index: 8284638 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7588. Min Act: -0.1700
Data Index: 6986636 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7432. Min Act: -0.1700
Data Index: 8033241 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7432. Min Act: -0.1700
Data Index: 4238320 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19