Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4883 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.7962. Min Act: -0.1700
Data Index: 4713588 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.7336. Min Act: -0.1700
Data Index: 8172665 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.7180. Min Act: -0.1700
Data Index: 6339943 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.7180. Min Act: -0.1700
Data Index: 5396616 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.6867. Min Act: -0.1700
Data Index: 1450917 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.6867. Min Act: -0.1700
Data Index: 2779603 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.6554. Min Act: -0.1700
Data Index: 7461875 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.6398. Min Act: -0.1700
Data Index: 6159095 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.6554. Min Act: -0.1700
Data Index: 3858715 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.6398. Min Act: -0.1700
Data Index: 4757946 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.6241. Min Act: -0.1700
Data Index: 1516162 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.5928. Min Act: -0.1700
Data Index: 274123 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.5928. Min Act: -0.1700
Data Index: 3661303 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.5772. Min Act: -0.1700
Data Index: 312354 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.5145. Min Act: -0.1700
Data Index: 4512657 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.5145. Min Act: -0.1700
Data Index: 913332 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.4989. Min Act: -0.1700
Data Index: 2798959 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.4832. Min Act: -0.1700
Data Index: 1279615 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.4989. Min Act: -0.1700
Data Index: 6689424 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7962. Min Range: -3.7962
Max Act: 3.4989. Min Act: -0.1700
Data Index: 5527103 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19