Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 433 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.6350. Min Act: -0.1700
Data Index: 6066659 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.6350. Min Act: -0.1700
Data Index: 3046895 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4787. Min Act: -0.1700
Data Index: 170702 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.4162. Min Act: -0.1700
Data Index: 6066657 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.3850. Min Act: -0.1700
Data Index: 1878219 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.3537. Min Act: -0.1700
Data Index: 3127211 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.3537. Min Act: -0.1700
Data Index: 1512172 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.2912. Min Act: -0.1700
Data Index: 1792722 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.2912. Min Act: -0.1700
Data Index: 8195250 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.2912. Min Act: -0.1700
Data Index: 6822837 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.2912. Min Act: -0.1700
Data Index: 7886072 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.2600. Min Act: -0.1700
Data Index: 6857411 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.2287. Min Act: -0.1700
Data Index: 4790543 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.2287. Min Act: -0.1700
Data Index: 3686441 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.1974. Min Act: -0.1700
Data Index: 3787752 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.1974. Min Act: -0.1700
Data Index: 4557604 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.1974. Min Act: -0.1700
Data Index: 1286073 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.1974. Min Act: -0.1700
Data Index: 6822844 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.1974. Min Act: -0.1700
Data Index: 2218639 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6350. Min Range: -4.6350
Max Act: 4.1974. Min Act: -0.1700
Data Index: 8195251 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19