Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4324 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.3938. Min Act: -0.1700
Data Index: 1600477 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1125. Min Act: -0.1700
Data Index: 5378620 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.0813. Min Act: -0.1700
Data Index: 8138169 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1125. Min Act: -0.1700
Data Index: 601003 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1125. Min Act: -0.1700
Data Index: 2482552 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.0500. Min Act: -0.1700
Data Index: 2429534 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.0188. Min Act: -0.1700
Data Index: 4168110 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9875. Min Act: -0.1700
Data Index: 2930599 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9875. Min Act: -0.1700
Data Index: 2803703 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9875. Min Act: -0.1700
Data Index: 4014503 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9563. Min Act: -0.1700
Data Index: 7971539 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9563. Min Act: -0.1700
Data Index: 8014808 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9563. Min Act: -0.1700
Data Index: 8019046 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9563. Min Act: -0.1700
Data Index: 6896217 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9250. Min Act: -0.1700
Data Index: 3507320 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9250. Min Act: -0.1700
Data Index: 4168109 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.9250. Min Act: -0.1700
Data Index: 6951122 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.8938. Min Act: -0.1700
Data Index: 5831242 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.8938. Min Act: -0.1700
Data Index: 4716991 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3938. Min Range: -5.3938
Max Act: 4.8938. Min Act: -0.1700
Data Index: 106141 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19