Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.8038. Min Act: -0.1700
Data Index: 5410670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.7726. Min Act: -0.1700
Data Index: 5406329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.7101. Min Act: -0.1700
Data Index: 3871709 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6476. Min Act: -0.1700
Data Index: 2805301 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6163. Min Act: -0.1700
Data Index: 204806 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6163. Min Act: -0.1700
Data Index: 5651531 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6163. Min Act: -0.1700
Data Index: 5843772 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6163. Min Act: -0.1700
Data Index: 1723637 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6163. Min Act: -0.1700
Data Index: 6461384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6163. Min Act: -0.1700
Data Index: 857850 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6163. Min Act: -0.1700
Data Index: 7531260 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.6163. Min Act: -0.1700
Data Index: 3871708 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.5851. Min Act: -0.1700
Data Index: 4233140 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.5226. Min Act: -0.1700
Data Index: 460183 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.4913. Min Act: -0.1700
Data Index: 4907752 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.4913. Min Act: -0.1700
Data Index: 2657784 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.4913. Min Act: -0.1700
Data Index: 7749969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.4913. Min Act: -0.1700
Data Index: 7568114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.4913. Min Act: -0.1700
Data Index: 5843771 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8038. Min Range: -4.8038
Max Act: 4.4288. Min Act: -0.1700
Data Index: 4029174 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19