Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.7945. Min Act: -0.1700
Data Index: 1099613 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.7945. Min Act: -0.1700
Data Index: 6902412 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.6382. Min Act: -0.1700
Data Index: 6213168 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.5132. Min Act: -0.1700
Data Index: 7555787 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.5132. Min Act: -0.1700
Data Index: 6466073 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.4195. Min Act: -0.1700
Data Index: 6395816 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.3570. Min Act: -0.1700
Data Index: 2557366 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.3570. Min Act: -0.1700
Data Index: 2557371 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.3257. Min Act: -0.1700
Data Index: 2908767 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.2632. Min Act: -0.1700
Data Index: 6516186 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.2007. Min Act: -0.1700
Data Index: 3340584 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.1695. Min Act: -0.1700
Data Index: 6060834 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.1695. Min Act: -0.1700
Data Index: 6701063 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.1382. Min Act: -0.1700
Data Index: 6426446 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.1070. Min Act: -0.1700
Data Index: 536529 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.1070. Min Act: -0.1700
Data Index: 4289323 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.0757. Min Act: -0.1700
Data Index: 1184086 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.0445. Min Act: -0.1700
Data Index: 3585332 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.0445. Min Act: -0.1700
Data Index: 7545350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7945. Min Range: -7.7945
Max Act: 7.0445. Min Act: -0.1700
Data Index: 5659755 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19