Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4101 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8925. Min Act: -0.1700
Data Index: 7644212 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8925. Min Act: -0.1700
Data Index: 2039261 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8612. Min Act: -0.1700
Data Index: 6113184 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8612. Min Act: -0.1700
Data Index: 604593 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8925. Min Act: -0.1697
Data Index: 2813959 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8612. Min Act: -0.1700
Data Index: 5165914 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8612. Min Act: -0.1700
Data Index: 4439684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8612. Min Act: -0.1700
Data Index: 475521 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8300. Min Act: -0.1700
Data Index: 937352 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8300. Min Act: -0.1700
Data Index: 5444479 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8300. Min Act: -0.1700
Data Index: 4176270 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.7987. Min Act: -0.1700
Data Index: 7805957 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8300. Min Act: -0.1700
Data Index: 3153736 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.8300. Min Act: -0.1700
Data Index: 7438231 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.7987. Min Act: -0.1700
Data Index: 2885829 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.7987. Min Act: -0.1700
Data Index: 2724074 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.7987. Min Act: -0.1700
Data Index: 446463 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.7987. Min Act: -0.1700
Data Index: 4748654 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.7987. Min Act: -0.1700
Data Index: 367008 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8925. Min Range: -3.8925
Max Act: 3.7987. Min Act: -0.1699
Data Index: 1361205 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19