Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.6743. Min Act: -0.1700
Data Index: 1791710 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.6430. Min Act: -0.1700
Data Index: 4742938 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.6118. Min Act: -0.1700
Data Index: 1030084 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.6118. Min Act: -0.1700
Data Index: 6133050 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.6118. Min Act: -0.1700
Data Index: 671494 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.5493. Min Act: -0.1700
Data Index: 8515561 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.5493. Min Act: -0.1700
Data Index: 5414473 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.5805. Min Act: -0.1700
Data Index: 7589724 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.5180. Min Act: -0.1700
Data Index: 8019243 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.4868. Min Act: -0.1700
Data Index: 3478248 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.4243. Min Act: -0.1700
Data Index: 4940620 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.4555. Min Act: -0.1700
Data Index: 3706419 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.4555. Min Act: -0.1700
Data Index: 8529697 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.4555. Min Act: -0.1700
Data Index: 565766 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.4555. Min Act: -0.1700
Data Index: 7193186 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.4243. Min Act: -0.1700
Data Index: 1128597 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.3930. Min Act: -0.1700
Data Index: 5242723 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.4243. Min Act: -0.1700
Data Index: 1791706 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.3930. Min Act: -0.1700
Data Index: 6905006 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6743. Min Range: -4.6743
Max Act: 4.3930. Min Act: -0.1700
Data Index: 2047580 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19