Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.6136. Min Act: -0.1700
Data Index: 8420061 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.5511. Min Act: -0.1700
Data Index: 6198697 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.4886. Min Act: -0.1700
Data Index: 8250938 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.4261. Min Act: -0.1700
Data Index: 2090565 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.4261. Min Act: -0.1700
Data Index: 6681129 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.4574. Min Act: -0.1700
Data Index: 3483901 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.4261. Min Act: -0.1700
Data Index: 1870064 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3011. Min Act: -0.1700
Data Index: 1910685 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3636. Min Act: -0.1700
Data Index: 7826741 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3636. Min Act: -0.1700
Data Index: 6475185 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3011. Min Act: -0.1700
Data Index: 385517 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3324. Min Act: -0.1700
Data Index: 6711905 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3636. Min Act: -0.1700
Data Index: 3207618 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3324. Min Act: -0.1700
Data Index: 5822285 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3011. Min Act: -0.1700
Data Index: 8688878 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.2699. Min Act: -0.1700
Data Index: 4372799 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.3011. Min Act: -0.1700
Data Index: 4546342 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.2699. Min Act: -0.1700
Data Index: 7112083 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.2699. Min Act: -0.1700
Data Index: 4405983 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6136. Min Range: -6.6136
Max Act: 6.2699. Min Act: -0.1700
Data Index: 948678 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19