Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4867 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.8739. Min Act: -0.1700
Data Index: 7560798 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.7802. Min Act: -0.1700
Data Index: 5285543 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.7177. Min Act: -0.1700
Data Index: 6420470 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5927. Min Act: -0.1700
Data Index: 5057541 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.5614. Min Act: -0.1700
Data Index: 6185192 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.4364. Min Act: -0.1700
Data Index: 6857537 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.3739. Min Act: -0.1700
Data Index: 2296842 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.4052. Min Act: -0.1700
Data Index: 4818257 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.3739. Min Act: -0.1700
Data Index: 2283532 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.3427. Min Act: -0.1700
Data Index: 7037030 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.3427. Min Act: -0.1700
Data Index: 475982 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.2802. Min Act: -0.1700
Data Index: 4353429 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.2802. Min Act: -0.1700
Data Index: 6039616 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.2802. Min Act: -0.1700
Data Index: 5814110 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.2802. Min Act: -0.1700
Data Index: 1389358 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.2802. Min Act: -0.1700
Data Index: 8736106 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.2489. Min Act: -0.1700
Data Index: 2646953 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.2489. Min Act: -0.1700
Data Index: 4397351 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.2489. Min Act: -0.1700
Data Index: 8087371 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8739. Min Range: -5.8739
Max Act: 5.1864. Min Act: -0.1700
Data Index: 5897024 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19