Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.7712. Min Act: -0.1700
Data Index: 3815073 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.6150. Min Act: -0.1700
Data Index: 545893 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.5837. Min Act: -0.1700
Data Index: 3793363 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4900. Min Act: -0.1700
Data Index: 2684417 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.5212. Min Act: -0.1700
Data Index: 7878187 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.5212. Min Act: -0.1700
Data Index: 1195793 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4587. Min Act: -0.1700
Data Index: 1560558 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4900. Min Act: -0.1700
Data Index: 1644193 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4900. Min Act: -0.1700
Data Index: 6507658 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4900. Min Act: -0.1700
Data Index: 4086173 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4587. Min Act: -0.1700
Data Index: 3542545 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4587. Min Act: -0.1700
Data Index: 7560490 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4275. Min Act: -0.1700
Data Index: 5310047 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.3962. Min Act: -0.1700
Data Index: 1470452 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4275. Min Act: -0.1700
Data Index: 2343649 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4275. Min Act: -0.1700
Data Index: 6406521 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.4275. Min Act: -0.1700
Data Index: 567060 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.3962. Min Act: -0.1700
Data Index: 6221954 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.3962. Min Act: -0.1700
Data Index: 1767105 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7712. Min Range: -5.7712
Max Act: 5.3962. Min Act: -0.1700
Data Index: 7626991 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19