Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4477 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.9249. Min Act: -0.1700
Data Index: 4183582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8932. Min Act: -0.1700
Data Index: 1639554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8615. Min Act: -0.1700
Data Index: 1425943 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8297. Min Act: -0.1700
Data Index: 8494239 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8297. Min Act: -0.1700
Data Index: 2639650 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 7605467 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8297. Min Act: -0.1700
Data Index: 1715119 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 4413638 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 6428263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 6615210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 8172351 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 4691265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 5572609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 6258623 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7341. Min Act: -0.1700
Data Index: 471981 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 7959195 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 7901027 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 4393925 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 2465013 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7341. Min Act: -0.1700
Data Index: 3854859 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19