Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.7583. Min Act: -0.1700
Data Index: 8560062 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.6958. Min Act: -0.1700
Data Index: 1234431 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.6021. Min Act: -0.1700
Data Index: 2019130 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.6021. Min Act: -0.1700
Data Index: 4655658 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.5396. Min Act: -0.1700
Data Index: 5906456 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.5396. Min Act: -0.1700
Data Index: 6035296 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.5083. Min Act: -0.1700
Data Index: 4664843 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.5083. Min Act: -0.1700
Data Index: 972745 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4771. Min Act: -0.1700
Data Index: 993352 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.5083. Min Act: -0.1700
Data Index: 2019131 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.5083. Min Act: -0.1700
Data Index: 5272381 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4146. Min Act: -0.1700
Data Index: 736349 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4458. Min Act: -0.1700
Data Index: 4810342 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4458. Min Act: -0.1700
Data Index: 5307087 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4458. Min Act: -0.1700
Data Index: 636658 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4458. Min Act: -0.1700
Data Index: 835540 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4458. Min Act: -0.1700
Data Index: 1038074 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4458. Min Act: -0.1700
Data Index: 3208319 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4146. Min Act: -0.1700
Data Index: 2635089 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7583. Min Range: -5.7583
Max Act: 5.4146. Min Act: -0.1700
Data Index: 2828536 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19