Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 964 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.4113. Min Act: -0.1700
Data Index: 6639824 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.3176. Min Act: -0.1700
Data Index: 836664 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.2863. Min Act: -0.1700
Data Index: 3685151 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.2863. Min Act: -0.1700
Data Index: 5386005 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1925. Min Act: -0.1700
Data Index: 3510829 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1925. Min Act: -0.1700
Data Index: 3871514 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1925. Min Act: -0.1700
Data Index: 3742724 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1925. Min Act: -0.1700
Data Index: 8120079 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1613. Min Act: -0.1700
Data Index: 8185155 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1300. Min Act: -0.1700
Data Index: 1483186 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1613. Min Act: -0.1700
Data Index: 8806189 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1613. Min Act: -0.1700
Data Index: 2396464 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1300. Min Act: -0.1700
Data Index: 860197 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.1300. Min Act: -0.1700
Data Index: 2001429 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.0988. Min Act: -0.1700
Data Index: 8559293 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.0988. Min Act: -0.1700
Data Index: 2437934 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.0988. Min Act: -0.1700
Data Index: 2008392 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.0988. Min Act: -0.1700
Data Index: 8745793 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.0988. Min Act: -0.1700
Data Index: 6360383 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4113. Min Range: -4.4113
Max Act: 4.0988. Min Act: -0.1700
Data Index: 2518815 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19