Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2368 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.9986. Min Act: -0.1700
Data Index: 8810913 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.5764. Min Act: -0.1700
Data Index: 6805547 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.5137. Min Act: -0.1700
Data Index: 2321535 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.4824. Min Act: -0.1700
Data Index: 2166222 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.4667. Min Act: -0.1700
Data Index: 6643215 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.4197. Min Act: -0.1700
Data Index: 2676361 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.4197. Min Act: -0.1700
Data Index: 4367271 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.4197. Min Act: -0.1700
Data Index: 1793379 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.4040. Min Act: -0.1700
Data Index: 6968431 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3884. Min Act: -0.1700
Data Index: 5251580 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3727. Min Act: -0.1700
Data Index: 4080316 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3570. Min Act: -0.1700
Data Index: 3356702 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3413. Min Act: -0.1700
Data Index: 8355883 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3570. Min Act: -0.1700
Data Index: 651821 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3570. Min Act: -0.1700
Data Index: 5184467 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3413. Min Act: -0.1700
Data Index: 5317037 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3570. Min Act: -0.1700
Data Index: 5932875 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3413. Min Act: -0.1700
Data Index: 5006745 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3256. Min Act: -0.1700
Data Index: 503678 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9986. Min Range: -3.9986
Max Act: 3.3413. Min Act: -0.1700
Data Index: 4407521 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19