Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.3300. Min Act: -0.1700
Data Index: 6808764 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.2986. Min Act: -0.1700
Data Index: 5458454 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.2986. Min Act: -0.1700
Data Index: 7274707 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.2515. Min Act: -0.1700
Data Index: 4082291 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.1729. Min Act: -0.1700
Data Index: 7523373 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.1257. Min Act: -0.1700
Data Index: 1504974 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.1257. Min Act: -0.1700
Data Index: 6446600 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.1099. Min Act: -0.1700
Data Index: 1686389 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0942. Min Act: -0.1700
Data Index: 4942945 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0942. Min Act: -0.1700
Data Index: 8772618 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0942. Min Act: -0.1700
Data Index: 7001972 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0942. Min Act: -0.1700
Data Index: 5733042 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0784. Min Act: -0.1700
Data Index: 5692570 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0784. Min Act: -0.1700
Data Index: 2153558 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0469. Min Act: -0.1700
Data Index: 1221909 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0784. Min Act: -0.1700
Data Index: 438651 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0626. Min Act: -0.1700
Data Index: 2348187 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0626. Min Act: -0.1700
Data Index: 531743 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0626. Min Act: -0.1700
Data Index: 6180179 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3300. Min Range: -3.3300
Max Act: 3.0469. Min Act: -0.1700
Data Index: 5300444 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19