Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.2492. Min Act: -0.1700
Data Index: 2318427 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.2492. Min Act: -0.1700
Data Index: 997038 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.2179. Min Act: -0.1700
Data Index: 5329587 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.1867. Min Act: -0.1700
Data Index: 4468523 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.1554. Min Act: -0.1700
Data Index: 7614537 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.1554. Min Act: -0.1700
Data Index: 4660706 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.1554. Min Act: -0.1700
Data Index: 8785501 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0929. Min Act: -0.1700
Data Index: 4154917 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.1242. Min Act: -0.1700
Data Index: 3033952 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0929. Min Act: -0.1700
Data Index: 1967904 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.1242. Min Act: -0.1700
Data Index: 4265240 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.1242. Min Act: -0.1700
Data Index: 6713185 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0929. Min Act: -0.1700
Data Index: 4329567 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0929. Min Act: -0.1700
Data Index: 6037427 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0929. Min Act: -0.1700
Data Index: 2664791 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0929. Min Act: -0.1700
Data Index: 2752248 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0304. Min Act: -0.1700
Data Index: 1319258 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0929. Min Act: -0.1700
Data Index: 4718752 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0617. Min Act: -0.1700
Data Index: 7586736 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2492. Min Range: -6.2492
Max Act: 6.0617. Min Act: -0.1700
Data Index: 4643766 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19