Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4835. Min Range: -4.4835
Max Act: 4.4835. Min Act: -0.1700
Data Index: 6541316 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4835. Min Range: -4.4835
Max Act: 4.2023. Min Act: -0.1700
Data Index: 1566630 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4835. Min Range: -4.4835
Max Act: 4.2335. Min Act: -0.1700
Data Index: 3168748 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4835. Min Range: -4.4835
Max Act: 4.0772. Min Act: -0.1700
Data Index: 8459702 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4835. Min Range: -4.4835
Max Act: 4.0147. Min Act: -0.1700
Data Index: 7353150 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4835. Min Range: -4.4835
Max Act: 4.0147. Min Act: -0.1700
Data Index: 8515818 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9835. Min Act: -0.1700
Data Index: 805052 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9835. Min Act: -0.1700
Data Index: 3886359 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9835. Min Act: -0.1700
Data Index: 2462322 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9835. Min Act: -0.1700
Data Index: 8560527 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9522. Min Act: -0.1700
Data Index: 4372800 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9522. Min Act: -0.1700
Data Index: 1929773 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9522. Min Act: -0.1700
Data Index: 6667432 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9209. Min Act: -0.1700
Data Index: 8560528 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.8897. Min Act: -0.1700
Data Index: 1547074 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.9209. Min Act: -0.1700
Data Index: 1511381 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.8897. Min Act: -0.1700
Data Index: 3778097 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.8897. Min Act: -0.1700
Data Index: 6931567 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.8271. Min Act: -0.1700
Data Index: 2661547 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4835. Min Range: -4.4835
Max Act: 3.8584. Min Act: -0.1700
Data Index: 3801272 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19