Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.5398. Min Act: -0.1700
Data Index: 7468831 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.5085. Min Act: -0.1700
Data Index: 3780232 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.3835. Min Act: -0.1700
Data Index: 3516216 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.3835. Min Act: -0.1700
Data Index: 3486543 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.3523. Min Act: -0.1700
Data Index: 4118385 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.2898. Min Act: -0.1700
Data Index: 2849669 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.2898. Min Act: -0.1700
Data Index: 5849069 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.2585. Min Act: -0.1700
Data Index: 3744935 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.2272. Min Act: -0.1700
Data Index: 3358906 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.2272. Min Act: -0.1700
Data Index: 1825909 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.2272. Min Act: -0.1700
Data Index: 3000241 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.1960. Min Act: -0.1700
Data Index: 669298 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.1960. Min Act: -0.1700
Data Index: 1150961 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.1960. Min Act: -0.1700
Data Index: 5212038 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.2272. Min Act: -0.1700
Data Index: 7771702 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.1960. Min Act: -0.1700
Data Index: 6639614 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.1960. Min Act: -0.1700
Data Index: 2608329 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.1960. Min Act: -0.1700
Data Index: 2293375 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.1960. Min Act: -0.1700
Data Index: 4472177 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5398. Min Range: -4.5398
Max Act: 4.1647. Min Act: -0.1700
Data Index: 2204015 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19