Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 132 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.7115. Min Act: -0.1700
Data Index: 2200719 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.4615. Min Act: -0.1700
Data Index: 4054765 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.2740. Min Act: -0.1700
Data Index: 3096298 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.2740. Min Act: -0.1700
Data Index: 4473950 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.2740. Min Act: -0.1700
Data Index: 3963710 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.2115. Min Act: -0.1700
Data Index: 3922299 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.2740. Min Act: -0.1700
Data Index: 4400409 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.2115. Min Act: -0.1700
Data Index: 318695 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.2115. Min Act: -0.1700
Data Index: 5194625 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.1490. Min Act: -0.1700
Data Index: 2397994 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 6571797 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 3791821 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 2900660 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 4197044 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 4721001 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 866532 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 3526125 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 3984597 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 3168027 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 3320882 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19