Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4017 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6208. Min Range: -6.6208
Max Act: 6.6208. Min Act: -0.1700
Data Index: 4762088 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6208. Min Range: -6.6208
Max Act: 6.2771. Min Act: -0.1700
Data Index: 7429084 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6208. Min Range: -6.6208
Max Act: 6.2458. Min Act: -0.1700
Data Index: 737181 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6208. Min Range: -6.6208
Max Act: 6.2146. Min Act: -0.1700
Data Index: 5994413 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8708. Min Act: -0.1700
Data Index: 1468903 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8708. Min Act: -0.1700
Data Index: 7426949 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8708. Min Act: -0.1700
Data Index: 7901391 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8396. Min Act: -0.1700
Data Index: 6907778 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8396. Min Act: -0.1700
Data Index: 4103057 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8396. Min Act: -0.1700
Data Index: 6164349 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8708. Min Act: -0.1700
Data Index: 4264486 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8396. Min Act: -0.1700
Data Index: 3325935 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.7771. Min Act: -0.1700
Data Index: 6767558 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.7458. Min Act: -0.1700
Data Index: 3139403 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5261767 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.8083. Min Act: -0.1700
Data Index: 6411360 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.7771. Min Act: -0.1700
Data Index: 4153246 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.7771. Min Act: -0.1700
Data Index: 1461666 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.7771. Min Act: -0.1700
Data Index: 4181682 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6208. Min Range: -6.6208
Max Act: 5.7146. Min Act: -0.1700
Data Index: 7311058 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19