Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.9612. Min Act: -0.1700
Data Index: 2842121 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.8362. Min Act: -0.1700
Data Index: 6619479 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.7112. Min Act: -0.1700
Data Index: 1892883 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.6487. Min Act: -0.1700
Data Index: 4503562 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.5862. Min Act: -0.1700
Data Index: 1933075 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.5862. Min Act: -0.1700
Data Index: 2207873 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.5237. Min Act: -0.1700
Data Index: 2624740 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.5237. Min Act: -0.1700
Data Index: 4669443 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.5237. Min Act: -0.1700
Data Index: 2757262 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.4612. Min Act: -0.1700
Data Index: 2409999 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.4612. Min Act: -0.1700
Data Index: 2411748 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.3987. Min Act: -0.1700
Data Index: 4451064 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.3987. Min Act: -0.1700
Data Index: 7510735 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.3987. Min Act: -0.1700
Data Index: 3927410 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.3987. Min Act: -0.1700
Data Index: 4531053 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.3362. Min Act: -0.1700
Data Index: 1006634 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.3362. Min Act: -0.1700
Data Index: 7402694 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.3362. Min Act: -0.1700
Data Index: 3024660 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.2737. Min Act: -0.1700
Data Index: 542533 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9612. Min Range: -8.9612
Max Act: 8.2737. Min Act: -0.1700
Data Index: 5096660 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19