Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.6835. Min Act: -0.1700
Data Index: 1897870 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.5272. Min Act: -0.1700
Data Index: 2408125 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.4335. Min Act: -0.1700
Data Index: 5155785 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.4022. Min Act: -0.1700
Data Index: 6961922 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.3710. Min Act: -0.1700
Data Index: 5984064 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.3085. Min Act: -0.1700
Data Index: 8574600 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.2772. Min Act: -0.1700
Data Index: 6928689 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.2460. Min Act: -0.1700
Data Index: 3216860 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.2460. Min Act: -0.1700
Data Index: 2465487 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.2147. Min Act: -0.1700
Data Index: 6514249 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.1835. Min Act: -0.1700
Data Index: 4312590 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.1522. Min Act: -0.1700
Data Index: 8502429 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.1210. Min Act: -0.1700
Data Index: 1335589 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.1210. Min Act: -0.1700
Data Index: 2900684 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.1210. Min Act: -0.1700
Data Index: 7002452 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.1210. Min Act: -0.1700
Data Index: 4371814 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.0585. Min Act: -0.1700
Data Index: 4117165 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.0585. Min Act: -0.1700
Data Index: 1318808 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.0272. Min Act: -0.1700
Data Index: 3485334 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6835. Min Range: -6.6835
Max Act: 6.0272. Min Act: -0.1700
Data Index: 2170932 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19