Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.3042. Min Act: -0.1700
Data Index: 4721478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1167. Min Act: -0.1700
Data Index: 8121670 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1167. Min Act: -0.1700
Data Index: 4305929 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1167. Min Act: -0.1700
Data Index: 4414985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0854. Min Act: -0.1700
Data Index: 7049814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0542. Min Act: -0.1700
Data Index: 876221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0542. Min Act: -0.1700
Data Index: 199920 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0542. Min Act: -0.1700
Data Index: 1170385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0542. Min Act: -0.1700
Data Index: 5783188 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0542. Min Act: -0.1700
Data Index: 6161159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0542. Min Act: -0.1700
Data Index: 4651223 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0542. Min Act: -0.1700
Data Index: 7335154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0229. Min Act: -0.1700
Data Index: 4699159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0229. Min Act: -0.1700
Data Index: 7943355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0229. Min Act: -0.1700
Data Index: 8201264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0229. Min Act: -0.1700
Data Index: 1220663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.0229. Min Act: -0.1700
Data Index: 3044585 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3042. Min Range: -4.3042
Max Act: 3.9916. Min Act: -0.1700
Data Index: 4655232 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3042. Min Range: -4.3042
Max Act: 3.9916. Min Act: -0.1700
Data Index: 987223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3042. Min Range: -4.3042
Max Act: 3.9916. Min Act: -0.1700
Data Index: 2277192 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19