Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2629 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.7835. Min Act: -0.1700
Data Index: 2818138 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.8147. Min Act: -0.1700
Data Index: 2913608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.7835. Min Act: -0.1700
Data Index: 1288693 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.7522. Min Act: -0.1700
Data Index: 8157813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.7522. Min Act: -0.1700
Data Index: 4549483 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6896. Min Act: -0.1700
Data Index: 4183274 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6583. Min Act: -0.1700
Data Index: 286433 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5957. Min Act: -0.1700
Data Index: 7639624 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5957. Min Act: -0.1700
Data Index: 5955316 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5957. Min Act: -0.1700
Data Index: 898007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5644. Min Act: -0.1700
Data Index: 4382124 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5644. Min Act: -0.1700
Data Index: 1210072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5644. Min Act: -0.1699
Data Index: 5429608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5331. Min Act: -0.1700
Data Index: 899181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5644. Min Act: -0.1700
Data Index: 5857055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5644. Min Act: -0.1700
Data Index: 6477651 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5644. Min Act: -0.1700
Data Index: 6947459 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5331. Min Act: -0.1700
Data Index: 2078296 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5644. Min Act: -0.1700
Data Index: 576796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5331. Min Act: -0.1700
Data Index: 4303765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19