Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 268 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.4758. Min Act: -0.1700
Data Index: 969595 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.4133. Min Act: -0.1700
Data Index: 7574279 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.2258. Min Act: -0.1700
Data Index: 1095135 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.1945. Min Act: -0.1700
Data Index: 6431371 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.1320. Min Act: -0.1700
Data Index: 2446754 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.1633. Min Act: -0.1700
Data Index: 4302129 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.1945. Min Act: -0.1700
Data Index: 6606137 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.1008. Min Act: -0.1700
Data Index: 8567993 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0695. Min Act: -0.1700
Data Index: 3789987 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0695. Min Act: -0.1700
Data Index: 49727 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0695. Min Act: -0.1700
Data Index: 2621660 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0695. Min Act: -0.1700
Data Index: 3528690 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0383. Min Act: -0.1700
Data Index: 6141625 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0383. Min Act: -0.1700
Data Index: 6102465 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0070. Min Act: -0.1700
Data Index: 3720809 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0070. Min Act: -0.1700
Data Index: 1406643 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4758. Min Range: -6.4758
Max Act: 6.0070. Min Act: -0.1700
Data Index: 4174996 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4758. Min Range: -6.4758
Max Act: 5.9758. Min Act: -0.1700
Data Index: 4819703 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4758. Min Range: -6.4758
Max Act: 5.9445. Min Act: -0.1700
Data Index: 7040050 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4758. Min Range: -6.4758
Max Act: 5.9445. Min Act: -0.1700
Data Index: 1182053 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19