Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8593. Min Range: -10.8593
Max Act: 10.8593. Min Act: -0.1700
Data Index: 8444206 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8593. Min Range: -10.8593
Max Act: 10.4843. Min Act: -0.1700
Data Index: 7949376 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8593. Min Range: -10.8593
Max Act: 10.3593. Min Act: -0.1700
Data Index: 116374 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8593. Min Range: -10.8593
Max Act: 10.1093. Min Act: -0.1700
Data Index: 7947985 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8593. Min Range: -10.8593
Max Act: 10.1093. Min Act: -0.1700
Data Index: 3328270 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8593. Min Range: -10.8593
Max Act: 10.0468. Min Act: -0.1700
Data Index: 8096711 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8593. Min Range: -10.8593
Max Act: 10.0468. Min Act: -0.1700
Data Index: 2803106 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.9843. Min Act: -0.1700
Data Index: 4010947 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.9218. Min Act: -0.1700
Data Index: 3099896 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.9218. Min Act: -0.1700
Data Index: 5220485 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.9218. Min Act: -0.1700
Data Index: 2732307 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.9218. Min Act: -0.1700
Data Index: 1041053 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.9218. Min Act: -0.1700
Data Index: 8563914 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.9218. Min Act: -0.1700
Data Index: 8516106 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.9843. Min Act: -0.1700
Data Index: 1090073 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.8593. Min Act: -0.1700
Data Index: 1935731 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.8593. Min Act: -0.1700
Data Index: 4076400 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.8593. Min Act: -0.1700
Data Index: 6890530 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.7968. Min Act: -0.1700
Data Index: 6894388 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8593. Min Range: -10.8593
Max Act: 9.8593. Min Act: -0.1700
Data Index: 4106135 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19