Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.8668. Min Act: -0.1700
Data Index: 3149453 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.5856. Min Act: -0.1700
Data Index: 658596 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.5543. Min Act: -0.1700
Data Index: 7618286 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.5231. Min Act: -0.1700
Data Index: 450506 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.4918. Min Act: -0.1700
Data Index: 6406314 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.4918. Min Act: -0.1700
Data Index: 5915752 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.4918. Min Act: -0.1700
Data Index: 8681158 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.4606. Min Act: -0.1700
Data Index: 4565119 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.4293. Min Act: -0.1700
Data Index: 806581 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.4293. Min Act: -0.1700
Data Index: 1609068 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.4293. Min Act: -0.1700
Data Index: 5620742 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.3981. Min Act: -0.1700
Data Index: 5312394 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.4293. Min Act: -0.1700
Data Index: 4329452 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.3668. Min Act: -0.1700
Data Index: 5839632 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.3356. Min Act: -0.1700
Data Index: 3045872 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.3356. Min Act: -0.1700
Data Index: 236176 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.3356. Min Act: -0.1700
Data Index: 366484 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.3356. Min Act: -0.1700
Data Index: 5607751 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.3043. Min Act: -0.1700
Data Index: 273310 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8668. Min Range: -4.8668
Max Act: 4.2731. Min Act: -0.1700
Data Index: 3781311 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19