Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1688 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.3605. Min Act: -0.1700
Data Index: 7102022 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2668. Min Act: -0.1700
Data Index: 717957 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2355. Min Act: -0.1700
Data Index: 5421063 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2355. Min Act: -0.1700
Data Index: 1250756 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2355. Min Act: -0.1700
Data Index: 8759568 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2355. Min Act: -0.1700
Data Index: 834541 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2355. Min Act: -0.1700
Data Index: 6418206 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2043. Min Act: -0.1700
Data Index: 5071414 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2043. Min Act: -0.1700
Data Index: 5654089 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2043. Min Act: -0.1700
Data Index: 1226360 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.2043. Min Act: -0.1700
Data Index: 716462 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1418. Min Act: -0.1700
Data Index: 8204379 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1730. Min Act: -0.1700
Data Index: 2910701 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1418. Min Act: -0.1700
Data Index: 1467833 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1418. Min Act: -0.1700
Data Index: 6119870 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1418. Min Act: -0.1700
Data Index: 6527700 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1105. Min Act: -0.1700
Data Index: 3693751 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1105. Min Act: -0.1700
Data Index: 4020673 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1105. Min Act: -0.1700
Data Index: 2661786 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1105. Min Act: -0.1700
Data Index: 6418636 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19