Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0128. Min Range: -4.0128
Max Act: 4.0128. Min Act: -0.1700
Data Index: 7395517 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0128. Min Range: -4.0128
Max Act: 4.0128. Min Act: -0.1700
Data Index: 165815 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0128. Min Range: -4.0128
Max Act: 4.0128. Min Act: -0.1700
Data Index: 4973594 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0128. Min Range: -4.0128
Max Act: 4.0128. Min Act: -0.1700
Data Index: 4467485 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0128. Min Range: -4.0128
Max Act: 4.0128. Min Act: -0.1700
Data Index: 2090257 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9816. Min Act: -0.1700
Data Index: 7646217 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9816. Min Act: -0.1700
Data Index: 1025874 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9816. Min Act: -0.1700
Data Index: 518828 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 6612285 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 5992983 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 2427221 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 1272240 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 2320117 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 2228035 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 386449 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 1839880 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 3748063 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9503. Min Act: -0.1700
Data Index: 3354835 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9190. Min Act: -0.1700
Data Index: 528357 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9190. Min Act: -0.1700
Data Index: 4243377 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19