Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3560. Min Range: -5.3560
Max Act: 5.3560. Min Act: -0.1700
Data Index: 6180467 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3560. Min Range: -5.3560
Max Act: 5.0122. Min Act: -0.1700
Data Index: 7917096 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.9810. Min Act: -0.1700
Data Index: 1602598 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.9497. Min Act: -0.1700
Data Index: 5554351 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.9497. Min Act: -0.1700
Data Index: 2792460 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.9185. Min Act: -0.1700
Data Index: 3408310 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.9185. Min Act: -0.1700
Data Index: 6502683 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.9185. Min Act: -0.1700
Data Index: 3408305 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.9185. Min Act: -0.1700
Data Index: 7361521 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8872. Min Act: -0.1700
Data Index: 7018517 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8872. Min Act: -0.1700
Data Index: 1327984 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8872. Min Act: -0.1700
Data Index: 7792927 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8872. Min Act: -0.1700
Data Index: 5906754 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8872. Min Act: -0.1700
Data Index: 5554339 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8872. Min Act: -0.1700
Data Index: 16883 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8560. Min Act: -0.1700
Data Index: 2542961 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8560. Min Act: -0.1700
Data Index: 5141479 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8560. Min Act: -0.1700
Data Index: 1111040 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8560. Min Act: -0.1700
Data Index: 6898824 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3560. Min Range: -5.3560
Max Act: 4.8247. Min Act: -0.1700
Data Index: 4442280 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19