Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.2685. Min Act: -0.1700
Data Index: 4313135 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0810. Min Act: -0.1700
Data Index: 2124500 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0810. Min Act: -0.1700
Data Index: 6516624 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0810. Min Act: -0.1700
Data Index: 3603322 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0498. Min Act: -0.1700
Data Index: 8746860 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0810. Min Act: -0.1700
Data Index: 5960741 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0498. Min Act: -0.1700
Data Index: 4359474 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0498. Min Act: -0.1700
Data Index: 7230181 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0498. Min Act: -0.1700
Data Index: 4313134 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0185. Min Act: -0.1700
Data Index: 7557384 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2685. Min Range: -6.2685
Max Act: 6.0185. Min Act: -0.1700
Data Index: 6647398 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9873. Min Act: -0.1700
Data Index: 3337966 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9873. Min Act: -0.1700
Data Index: 5287131 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9873. Min Act: -0.1700
Data Index: 7199206 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9560. Min Act: -0.1700
Data Index: 2557916 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9560. Min Act: -0.1700
Data Index: 7472101 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9560. Min Act: -0.1700
Data Index: 4164216 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9248. Min Act: -0.1700
Data Index: 970292 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9248. Min Act: -0.1700
Data Index: 1505338 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2685. Min Range: -6.2685
Max Act: 5.9248. Min Act: -0.1700
Data Index: 7976278 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19