Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4660 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.9119. Min Act: -0.1700
Data Index: 8764768 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6306. Min Act: -0.1700
Data Index: 3617153 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.5369. Min Act: -0.1700
Data Index: 2475438 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.5681. Min Act: -0.1700
Data Index: 3228608 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.5056. Min Act: -0.1700
Data Index: 4147084 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.4744. Min Act: -0.1700
Data Index: 481859 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.4431. Min Act: -0.1700
Data Index: 8712574 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3806. Min Act: -0.1700
Data Index: 3243998 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.4119. Min Act: -0.1700
Data Index: 2315858 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.4119. Min Act: -0.1700
Data Index: 8499726 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3806. Min Act: -0.1700
Data Index: 516351 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3806. Min Act: -0.1700
Data Index: 5558967 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3806. Min Act: -0.1700
Data Index: 542525 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3493. Min Act: -0.1700
Data Index: 364198 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3806. Min Act: -0.1700
Data Index: 7070745 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3806. Min Act: -0.1700
Data Index: 4316258 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3493. Min Act: -0.1700
Data Index: 2470802 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3493. Min Act: -0.1700
Data Index: 7361709 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3493. Min Act: -0.1700
Data Index: 6349159 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3493. Min Act: -0.1700
Data Index: 1314009 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19