Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2171 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.8209. Min Act: -0.1700
Data Index: 3675517 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.6334. Min Act: -0.1700
Data Index: 4643040 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.5709. Min Act: -0.1700
Data Index: 2200463 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.6021. Min Act: -0.1700
Data Index: 7462220 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.5396. Min Act: -0.1700
Data Index: 5435174 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.5396. Min Act: -0.1700
Data Index: 3352131 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.5084. Min Act: -0.1700
Data Index: 4923309 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.5084. Min Act: -0.1700
Data Index: 6645907 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.5084. Min Act: -0.1700
Data Index: 7462221 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.5396. Min Act: -0.1700
Data Index: 5565351 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4771. Min Act: -0.1700
Data Index: 8533835 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4771. Min Act: -0.1700
Data Index: 220638 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4146. Min Act: -0.1700
Data Index: 4999268 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4459. Min Act: -0.1700
Data Index: 5818133 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4459. Min Act: -0.1700
Data Index: 8003714 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4459. Min Act: -0.1700
Data Index: 2884837 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4146. Min Act: -0.1700
Data Index: 5880949 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4146. Min Act: -0.1700
Data Index: 5237054 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.4146. Min Act: -0.1700
Data Index: 4594055 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8209. Min Range: -4.8209
Max Act: 4.3834. Min Act: -0.1700
Data Index: 1369120 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19