Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3360. Min Range: -6.3360
Max Act: 6.3360. Min Act: -0.1700
Data Index: 4055848 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3360. Min Range: -6.3360
Max Act: 6.2735. Min Act: -0.1700
Data Index: 2305000 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3360. Min Range: -6.3360
Max Act: 6.1173. Min Act: -0.1700
Data Index: 7438195 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.9610. Min Act: -0.1700
Data Index: 1840934 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.9298. Min Act: -0.1700
Data Index: 3409677 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.9298. Min Act: -0.1700
Data Index: 1280741 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.8673. Min Act: -0.1700
Data Index: 1687370 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.8673. Min Act: -0.1700
Data Index: 1589961 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.8360. Min Act: -0.1700
Data Index: 8142897 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.8360. Min Act: -0.1700
Data Index: 1332063 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.8048. Min Act: -0.1700
Data Index: 3512272 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7733377 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7676195 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.7423. Min Act: -0.1700
Data Index: 4526183 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.7423. Min Act: -0.1700
Data Index: 7323270 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.6798. Min Act: -0.1700
Data Index: 6863552 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.7110. Min Act: -0.1700
Data Index: 4365441 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.6798. Min Act: -0.1700
Data Index: 2658347 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.7110. Min Act: -0.1700
Data Index: 1713563 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3360. Min Range: -6.3360
Max Act: 5.7110. Min Act: -0.1700
Data Index: 8825413 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19