Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.8645. Min Act: -0.1700
Data Index: 3839150 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.4895. Min Act: -0.1700
Data Index: 3520017 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.4895. Min Act: -0.1700
Data Index: 3805819 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.4582. Min Act: -0.1700
Data Index: 4522565 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.4270. Min Act: -0.1700
Data Index: 8786868 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.3957. Min Act: -0.1700
Data Index: 4500082 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.4270. Min Act: -0.1700
Data Index: 5887154 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.3645. Min Act: -0.1700
Data Index: 1998688 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.3645. Min Act: -0.1700
Data Index: 451514 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.3020. Min Act: -0.1700
Data Index: 8549413 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.2395. Min Act: -0.1700
Data Index: 4908219 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.2395. Min Act: -0.1700
Data Index: 5074067 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.2395. Min Act: -0.1700
Data Index: 4500077 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.2395. Min Act: -0.1700
Data Index: 4126155 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.2082. Min Act: -0.1700
Data Index: 2964671 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.1770. Min Act: -0.1700
Data Index: 7617352 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.1457. Min Act: -0.1700
Data Index: 6725223 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.1457. Min Act: -0.1700
Data Index: 1964242 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.1770. Min Act: -0.1700
Data Index: 4249272 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8645. Min Range: -5.8645
Max Act: 5.1457. Min Act: -0.1700
Data Index: 7642241 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19