Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1576 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0329. Min Range: -4.0329
Max Act: 4.0329. Min Act: -0.1700
Data Index: 4864974 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.9704. Min Act: -0.1700
Data Index: 2657339 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0329. Min Range: -4.0329
Max Act: 4.0016. Min Act: -0.1700
Data Index: 4361356 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.9391. Min Act: -0.1700
Data Index: 5509665 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.9391. Min Act: -0.1700
Data Index: 6219666 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.9079. Min Act: -0.1700
Data Index: 5428700 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8922. Min Act: -0.1700
Data Index: 6302087 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8922. Min Act: -0.1700
Data Index: 1658332 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8922. Min Act: -0.1700
Data Index: 4345540 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8922. Min Act: -0.1700
Data Index: 4656184 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8610. Min Act: -0.1700
Data Index: 3958094 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8766. Min Act: -0.1700
Data Index: 2133184 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8610. Min Act: -0.1700
Data Index: 2629473 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8453. Min Act: -0.1700
Data Index: 772965 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8610. Min Act: -0.1700
Data Index: 3287640 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8297. Min Act: -0.1700
Data Index: 5752135 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8297. Min Act: -0.1700
Data Index: 602498 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8140. Min Act: -0.1700
Data Index: 3210117 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8297. Min Act: -0.1700
Data Index: 2994106 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0329. Min Range: -4.0329
Max Act: 3.8297. Min Act: -0.1700
Data Index: 528510 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19