Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1909 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.8601. Min Act: -0.1700
Data Index: 737362 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.8288. Min Act: -0.1700
Data Index: 6396716 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.7663. Min Act: -0.1700
Data Index: 4884158 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.6726. Min Act: -0.1700
Data Index: 6516923 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.7038. Min Act: -0.1700
Data Index: 3909123 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.6726. Min Act: -0.1700
Data Index: 376150 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.6413. Min Act: -0.1700
Data Index: 2215706 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.6101. Min Act: -0.1700
Data Index: 7323599 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5788. Min Act: -0.1700
Data Index: 8568563 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5788. Min Act: -0.1700
Data Index: 4103416 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5476. Min Act: -0.1700
Data Index: 4101084 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5476. Min Act: -0.1700
Data Index: 4220685 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5476. Min Act: -0.1700
Data Index: 3610783 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5163. Min Act: -0.1700
Data Index: 6983165 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5476. Min Act: -0.1700
Data Index: 6264165 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5476. Min Act: -0.1700
Data Index: 8521371 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5476. Min Act: -0.1700
Data Index: 7932631 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.5163. Min Act: -0.1700
Data Index: 7297740 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.4851. Min Act: -0.1700
Data Index: 1687889 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8601. Min Range: -6.8601
Max Act: 6.4851. Min Act: -0.1700
Data Index: 4098104 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19