Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5032 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.8145. Min Act: -0.1700
Data Index: 4549798 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.7520. Min Act: -0.1700
Data Index: 5961099 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.7520. Min Act: -0.1700
Data Index: 584605 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.7520. Min Act: -0.1700
Data Index: 2909719 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.7520. Min Act: -0.1700
Data Index: 7395543 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.7520. Min Act: -0.1700
Data Index: 2301251 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.7520. Min Act: -0.1700
Data Index: 3356070 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.7520. Min Act: -0.1700
Data Index: 5342127 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.6895. Min Act: -0.1700
Data Index: 8616352 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.6895. Min Act: -0.1700
Data Index: 5641213 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.6895. Min Act: -0.1700
Data Index: 5541468 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.6895. Min Act: -0.1700
Data Index: 6333357 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.6270. Min Act: -0.1700
Data Index: 2738402 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.6270. Min Act: -0.1700
Data Index: 2221386 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.6270. Min Act: -0.1700
Data Index: 5769993 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.5020. Min Act: -0.1698
Data Index: 6234836 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.5645. Min Act: -0.1700
Data Index: 932466 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.6270. Min Act: -0.1699
Data Index: 4184945 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.5645. Min Act: -0.1700
Data Index: 4221248 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8145. Min Range: -7.8145
Max Act: 7.5645. Min Act: -0.1700
Data Index: 3296042 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19