Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.2925. Min Act: -0.1700
Data Index: 7077141 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.2612. Min Act: -0.1700
Data Index: 6138502 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1675. Min Act: -0.1700
Data Index: 168247 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1362. Min Act: -0.1700
Data Index: 6080099 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1362. Min Act: -0.1700
Data Index: 7943226 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1362. Min Act: -0.1700
Data Index: 5614679 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1050. Min Act: -0.1700
Data Index: 4373300 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1050. Min Act: -0.1700
Data Index: 6145162 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0425. Min Act: -0.1700
Data Index: 6754238 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1050. Min Act: -0.1700
Data Index: 5994411 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1050. Min Act: -0.1700
Data Index: 276612 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.1050. Min Act: -0.1700
Data Index: 3439866 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0737. Min Act: -0.1700
Data Index: 758114 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0425. Min Act: -0.1700
Data Index: 5650228 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0737. Min Act: -0.1700
Data Index: 919907 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0737. Min Act: -0.1700
Data Index: 2798187 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0737. Min Act: -0.1700
Data Index: 1794575 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0112. Min Act: -0.1700
Data Index: 2249482 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0112. Min Act: -0.1700
Data Index: 5535071 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2925. Min Range: -5.2925
Max Act: 5.0112. Min Act: -0.1700
Data Index: 6298790 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19