Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1206. Min Range: -5.1206
Max Act: 5.1206. Min Act: -0.1700
Data Index: 4236532 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.9331. Min Act: -0.1700
Data Index: 5170405 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.9019. Min Act: -0.1700
Data Index: 7374582 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.9019. Min Act: -0.1700
Data Index: 7980077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.8706. Min Act: -0.1700
Data Index: 8538228 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.7769. Min Act: -0.1700
Data Index: 2832177 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.7769. Min Act: -0.1700
Data Index: 6206085 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.7769. Min Act: -0.1700
Data Index: 5678205 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.7769. Min Act: -0.1700
Data Index: 152767 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.7456. Min Act: -0.1700
Data Index: 2683279 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.7144. Min Act: -0.1700
Data Index: 4236531 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.6831. Min Act: -0.1700
Data Index: 1487411 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1984237 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.6206. Min Act: -0.1700
Data Index: 1660741 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.6519. Min Act: -0.1700
Data Index: 5399532 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.6206. Min Act: -0.1700
Data Index: 8250937 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.6519. Min Act: -0.1700
Data Index: 6962853 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.6206. Min Act: -0.1700
Data Index: 1476753 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.5894. Min Act: -0.1700
Data Index: 7902723 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1206. Min Range: -5.1206
Max Act: 4.5894. Min Act: -0.1700
Data Index: 1476756 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19