Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1947 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.5864. Min Act: -0.1700
Data Index: 1789922 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.4614. Min Act: -0.1700
Data Index: 8018855 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.4301. Min Act: -0.1700
Data Index: 853426 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.4301. Min Act: -0.1700
Data Index: 4254726 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.4301. Min Act: -0.1700
Data Index: 3441803 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3989. Min Act: -0.1700
Data Index: 6713901 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3989. Min Act: -0.1700
Data Index: 674422 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3989. Min Act: -0.1700
Data Index: 1212521 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3676. Min Act: -0.1700
Data Index: 6444293 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3989. Min Act: -0.1700
Data Index: 5701412 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3989. Min Act: -0.1700
Data Index: 8412173 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3989. Min Act: -0.1700
Data Index: 1583461 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3676. Min Act: -0.1700
Data Index: 8737117 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3676. Min Act: -0.1700
Data Index: 401202 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3676. Min Act: -0.1700
Data Index: 5099651 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3676. Min Act: -0.1700
Data Index: 4374788 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3676. Min Act: -0.1700
Data Index: 8407983 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3676. Min Act: -0.1700
Data Index: 4280287 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3364. Min Act: -0.1700
Data Index: 1149079 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5864. Min Range: -5.5864
Max Act: 5.3676. Min Act: -0.1700
Data Index: 8074783 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19