Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4835. Min Range: -6.4835
Max Act: 6.4835. Min Act: -0.1700
Data Index: 5746580 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4835. Min Range: -6.4835
Max Act: 6.3272. Min Act: -0.1700
Data Index: 669205 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.9522. Min Act: -0.1700
Data Index: 5311885 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.9210. Min Act: -0.1700
Data Index: 165632 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.8897. Min Act: -0.1700
Data Index: 8266958 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.8585. Min Act: -0.1700
Data Index: 673981 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7960. Min Act: -0.1700
Data Index: 2350929 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7960. Min Act: -0.1700
Data Index: 6620553 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7960. Min Act: -0.1700
Data Index: 5713768 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7647. Min Act: -0.1700
Data Index: 7959562 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7647. Min Act: -0.1700
Data Index: 6544700 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7647. Min Act: -0.1700
Data Index: 5752914 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7335. Min Act: -0.1700
Data Index: 7062837 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7335. Min Act: -0.1700
Data Index: 874699 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7022. Min Act: -0.1700
Data Index: 798597 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.6710. Min Act: -0.1700
Data Index: 8750819 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7022. Min Act: -0.1700
Data Index: 6114416 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.6710. Min Act: -0.1700
Data Index: 5750102 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.7022. Min Act: -0.1700
Data Index: 8548621 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4835. Min Range: -6.4835
Max Act: 5.6397. Min Act: -0.1700
Data Index: 3226104 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19