Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.7560. Min Act: -0.1700
Data Index: 5807460 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.6935. Min Act: -0.1700
Data Index: 1465433 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.6623. Min Act: -0.1700
Data Index: 911401 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.6623. Min Act: -0.1700
Data Index: 7049137 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.6310. Min Act: -0.1700
Data Index: 3925961 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.5998. Min Act: -0.1699
Data Index: 3740194 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.5685. Min Act: -0.1700
Data Index: 8252117 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.5373. Min Act: -0.1700
Data Index: 6363440 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.5373. Min Act: -0.1700
Data Index: 6138738 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.5060. Min Act: -0.1699
Data Index: 2983666 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4435. Min Act: -0.1700
Data Index: 3897993 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4435. Min Act: -0.1700
Data Index: 6216767 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4435. Min Act: -0.1700
Data Index: 2953790 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4123. Min Act: -0.1700
Data Index: 4248670 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4123. Min Act: -0.1700
Data Index: 4025281 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4123. Min Act: -0.1700
Data Index: 6356260 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4123. Min Act: -0.1699
Data Index: 4995460 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4123. Min Act: -0.1700
Data Index: 247978 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4123. Min Act: -0.1700
Data Index: 3743499 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3810. Min Act: -0.1700
Data Index: 4694402 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19