Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.4281. Min Act: -0.1700
Data Index: 3466728 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.4125. Min Act: -0.1700
Data Index: 7467888 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3811. Min Act: -0.1700
Data Index: 4530686 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3497. Min Act: -0.1700
Data Index: 4698804 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3654. Min Act: -0.1700
Data Index: 6560363 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3497. Min Act: -0.1700
Data Index: 7467893 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3340. Min Act: -0.1700
Data Index: 7432690 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3497. Min Act: -0.1700
Data Index: 1991520 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3183. Min Act: -0.1700
Data Index: 844401 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3183. Min Act: -0.1700
Data Index: 7453770 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3183. Min Act: -0.1700
Data Index: 3491107 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3183. Min Act: -0.1700
Data Index: 3677179 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3026. Min Act: -0.1700
Data Index: 753531 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3183. Min Act: -0.1700
Data Index: 7467892 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3183. Min Act: -0.1700
Data Index: 7467891 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3026. Min Act: -0.1700
Data Index: 3300661 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3026. Min Act: -0.1700
Data Index: 2375135 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.3026. Min Act: -0.1700
Data Index: 1412888 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.2869. Min Act: -0.1700
Data Index: 7203394 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4281. Min Range: -3.4281
Max Act: 3.2869. Min Act: -0.1700
Data Index: 5467676 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19