Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 154 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.7967. Min Act: -0.1700
Data Index: 6506545 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.7342. Min Act: -0.1700
Data Index: 8333115 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.2967. Min Act: -0.1700
Data Index: 1736809 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.2967. Min Act: -0.1700
Data Index: 4605205 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.2967. Min Act: -0.1700
Data Index: 7041280 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.3592. Min Act: -0.1700
Data Index: 3871552 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.1717. Min Act: -0.1700
Data Index: 2554973 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.1717. Min Act: -0.1700
Data Index: 4854508 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.1717. Min Act: -0.1700
Data Index: 3924041 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.1717. Min Act: -0.1700
Data Index: 4984370 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.0467. Min Act: -0.1700
Data Index: 3610971 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.1092. Min Act: -0.1700
Data Index: 4224050 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.1092. Min Act: -0.1700
Data Index: 1652699 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.1092. Min Act: -0.1700
Data Index: 8394842 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.1092. Min Act: -0.1700
Data Index: 2655703 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.0467. Min Act: -0.1700
Data Index: 7332767 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7967. Min Range: -9.7967
Max Act: 8.9842. Min Act: -0.1700
Data Index: 5566704 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7967. Min Range: -9.7967
Max Act: 9.0467. Min Act: -0.1700
Data Index: 5551447 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7967. Min Range: -9.7967
Max Act: 8.9842. Min Act: -0.1700
Data Index: 1257673 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7967. Min Range: -9.7967
Max Act: 8.9842. Min Act: -0.1700
Data Index: 7609647 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19