Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4241 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2533. Min Range: -4.2533
Max Act: 4.2533. Min Act: -0.1700
Data Index: 8464813 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.9720. Min Act: -0.1700
Data Index: 7606026 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.9407. Min Act: -0.1700
Data Index: 8067761 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.9095. Min Act: -0.1700
Data Index: 7739398 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.9095. Min Act: -0.1700
Data Index: 8188100 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.8782. Min Act: -0.1700
Data Index: 1222116 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.8626. Min Act: -0.1700
Data Index: 6954091 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.8626. Min Act: -0.1700
Data Index: 1366527 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.8313. Min Act: -0.1700
Data Index: 3921752 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.8000. Min Act: -0.1700
Data Index: 6715338 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.8000. Min Act: -0.1700
Data Index: 3665442 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.8000. Min Act: -0.1700
Data Index: 8386846 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.7844. Min Act: -0.1700
Data Index: 6763639 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.7844. Min Act: -0.1700
Data Index: 2496980 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.7844. Min Act: -0.1700
Data Index: 3252877 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.7844. Min Act: -0.1700
Data Index: 1550616 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.7844. Min Act: -0.1700
Data Index: 1388115 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.7844. Min Act: -0.1700
Data Index: 4464766 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.7844. Min Act: -0.1700
Data Index: 3798489 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2533. Min Range: -4.2533
Max Act: 3.7687. Min Act: -0.1700
Data Index: 7669590 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19