Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2350. Min Range: -3.2350
Max Act: 3.2350. Min Act: -0.1700
Data Index: 1475893 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2350. Min Range: -3.2350
Max Act: 3.1406. Min Act: -0.1700
Data Index: 7610455 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2350. Min Range: -3.2350
Max Act: 3.1091. Min Act: -0.1700
Data Index: 6126524 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2350. Min Range: -3.2350
Max Act: 3.1249. Min Act: -0.1700
Data Index: 958966 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2350. Min Range: -3.2350
Max Act: 3.0303. Min Act: -0.1700
Data Index: 5276726 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2350. Min Range: -3.2350
Max Act: 3.0303. Min Act: -0.1700
Data Index: 3415186 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2350. Min Range: -3.2350
Max Act: 3.0303. Min Act: -0.1700
Data Index: 3556700 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2350. Min Range: -3.2350
Max Act: 3.0145. Min Act: -0.1700
Data Index: 7604002 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.9671. Min Act: -0.1700
Data Index: 2946424 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.9671. Min Act: -0.1700
Data Index: 2356577 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.9196. Min Act: -0.1700
Data Index: 7898637 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.9037. Min Act: -0.1700
Data Index: 2259766 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.9037. Min Act: -0.1700
Data Index: 8163632 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.9037. Min Act: -0.1700
Data Index: 1162360 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.9037. Min Act: -0.1700
Data Index: 6124158 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.8878. Min Act: -0.1700
Data Index: 617784 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.8878. Min Act: -0.1700
Data Index: 3273990 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.8561. Min Act: -0.1700
Data Index: 8571605 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.8720. Min Act: -0.1700
Data Index: 4196461 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2350. Min Range: -3.2350
Max Act: 2.8561. Min Act: -0.1700
Data Index: 7208817 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19