Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.9538. Min Act: -0.1700
Data Index: 471062 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.9538. Min Act: -0.1700
Data Index: 7202709 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.9226. Min Act: -0.1700
Data Index: 5854858 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2077539 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2450638 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.9538. Min Act: -0.1700
Data Index: 5205413 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 4131492 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 362997 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 6335924 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 2170266 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 8343243 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 4962232 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.7976. Min Act: -0.1700
Data Index: 6676636 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.7663. Min Act: -0.1700
Data Index: 2822724 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.7038. Min Act: -0.1700
Data Index: 2587040 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.6726. Min Act: -0.1700
Data Index: 856086 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.6726. Min Act: -0.1700
Data Index: 4743913 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.6413. Min Act: -0.1700
Data Index: 4431861 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.6101. Min Act: -0.1700
Data Index: 1028796 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9538. Min Range: -4.9538
Max Act: 4.6101. Min Act: -0.1700
Data Index: 5466300 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19