Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0845. Min Range: -7.0845
Max Act: 7.0845. Min Act: -0.1700
Data Index: 1555328 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.7407. Min Act: -0.1700
Data Index: 7448834 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.7095. Min Act: -0.1700
Data Index: 5895426 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.6782. Min Act: -0.1700
Data Index: 5496548 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.6782. Min Act: -0.1700
Data Index: 1685896 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.6470. Min Act: -0.1700
Data Index: 2287398 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.6157. Min Act: -0.1700
Data Index: 2273613 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.4595. Min Act: -0.1700
Data Index: 5385433 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.4595. Min Act: -0.1700
Data Index: 1807430 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.4595. Min Act: -0.1700
Data Index: 8758271 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.4282. Min Act: -0.1700
Data Index: 1853954 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3970. Min Act: -0.1700
Data Index: 991552 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3970. Min Act: -0.1700
Data Index: 5883723 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3345. Min Act: -0.1700
Data Index: 1110436 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3657. Min Act: -0.1700
Data Index: 8158218 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3657. Min Act: -0.1700
Data Index: 5801675 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3657. Min Act: -0.1700
Data Index: 3713677 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3657. Min Act: -0.1700
Data Index: 3756397 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3345. Min Act: -0.1700
Data Index: 2724037 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0845. Min Range: -7.0845
Max Act: 6.3657. Min Act: -0.1700
Data Index: 5685308 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19