Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.6395. Min Act: -0.1700
Data Index: 549779 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.3270. Min Act: -0.1700
Data Index: 8317482 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2958. Min Act: -0.1700
Data Index: 5763161 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2958. Min Act: -0.1700
Data Index: 9294 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2333. Min Act: -0.1700
Data Index: 5466669 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2020. Min Act: -0.1700
Data Index: 2120483 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2333. Min Act: -0.1700
Data Index: 4669171 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2333. Min Act: -0.1700
Data Index: 157444 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2333. Min Act: -0.1700
Data Index: 7831029 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2333. Min Act: -0.1700
Data Index: 3526270 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2020. Min Act: -0.1700
Data Index: 4104902 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2020. Min Act: -0.1700
Data Index: 4222238 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2020. Min Act: -0.1700
Data Index: 5285640 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2020. Min Act: -0.1700
Data Index: 176493 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.2020. Min Act: -0.1700
Data Index: 2940867 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.1708. Min Act: -0.1700
Data Index: 1157153 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.1708. Min Act: -0.1700
Data Index: 4888481 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.1708. Min Act: -0.1700
Data Index: 4700836 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.1708. Min Act: -0.1700
Data Index: 3940800 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6395. Min Range: -5.6395
Max Act: 5.1708. Min Act: -0.1700
Data Index: 4340179 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19