Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2306 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.8451. Min Act: -0.1700
Data Index: 2142312 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.8138. Min Act: -0.1700
Data Index: 8198718 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.7826. Min Act: -0.1700
Data Index: 7119290 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.7201. Min Act: -0.1700
Data Index: 8471726 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.7201. Min Act: -0.1700
Data Index: 2484649 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.6576. Min Act: -0.1700
Data Index: 2938659 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.6263. Min Act: -0.1700
Data Index: 7219065 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.6576. Min Act: -0.1700
Data Index: 1561755 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.6263. Min Act: -0.1700
Data Index: 3990998 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5951. Min Act: -0.1700
Data Index: 7219063 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5951. Min Act: -0.1700
Data Index: 7219076 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5326. Min Act: -0.1700
Data Index: 520903 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5638. Min Act: -0.1700
Data Index: 2451375 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5638. Min Act: -0.1700
Data Index: 2938652 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5638. Min Act: -0.1700
Data Index: 5053665 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5638. Min Act: -0.1700
Data Index: 2938642 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5326. Min Act: -0.1700
Data Index: 7558325 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5326. Min Act: -0.1700
Data Index: 7219071 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5326. Min Act: -0.1700
Data Index: 2938658 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8451. Min Range: -6.8451
Max Act: 6.5326. Min Act: -0.1700
Data Index: 1561750 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19