Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5469. Min Range: -7.5469
Max Act: 7.5469. Min Act: -0.1700
Data Index: 2018089 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.7969. Min Act: -0.1700
Data Index: 7604599 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.5781. Min Act: -0.1700
Data Index: 7906614 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.5156. Min Act: -0.1700
Data Index: 1977677 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.4844. Min Act: -0.1700
Data Index: 8325697 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.4531. Min Act: -0.1700
Data Index: 6653796 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.4531. Min Act: -0.1700
Data Index: 4050955 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.4531. Min Act: -0.1700
Data Index: 3198447 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.3906. Min Act: -0.1700
Data Index: 784802 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.4219. Min Act: -0.1700
Data Index: 3839402 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.3594. Min Act: -0.1700
Data Index: 8065447 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.4219. Min Act: -0.1700
Data Index: 5551327 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.3281. Min Act: -0.1700
Data Index: 3349984 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.3281. Min Act: -0.1700
Data Index: 2103204 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.3281. Min Act: -0.1700
Data Index: 8141801 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.3281. Min Act: -0.1700
Data Index: 3474131 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.2656. Min Act: -0.1700
Data Index: 4200482 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.2969. Min Act: -0.1699
Data Index: 8477388 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.2969. Min Act: -0.1700
Data Index: 1284431 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5469. Min Range: -7.5469
Max Act: 6.2656. Min Act: -0.1700
Data Index: 1580732 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19