Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6367 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.4896. Min Act: -0.1700
Data Index: 3929543 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.4271. Min Act: -0.1700
Data Index: 2848686 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3959. Min Act: -0.1700
Data Index: 5796937 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3646. Min Act: -0.1700
Data Index: 5345319 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3646. Min Act: -0.1700
Data Index: 5948261 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3646. Min Act: -0.1700
Data Index: 7800022 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3021. Min Act: -0.1700
Data Index: 1128137 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3334. Min Act: -0.1700
Data Index: 4666656 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3334. Min Act: -0.1700
Data Index: 3415135 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3021. Min Act: -0.1700
Data Index: 5507158 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3021. Min Act: -0.1700
Data Index: 4498890 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.3021. Min Act: -0.1700
Data Index: 5525385 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.2709. Min Act: -0.1700
Data Index: 7541646 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.2709. Min Act: -0.1700
Data Index: 2167851 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.2709. Min Act: -0.1700
Data Index: 2209572 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.2709. Min Act: -0.1700
Data Index: 5580789 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.2709. Min Act: -0.1700
Data Index: 5217891 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.2396. Min Act: -0.1700
Data Index: 5083340 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.2396. Min Act: -0.1700
Data Index: 2891972 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4896. Min Range: -6.4896
Max Act: 6.2396. Min Act: -0.1700
Data Index: 4481160 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19