Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1218 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.5399. Min Act: -0.1700
Data Index: 1312519 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.4146. Min Act: -0.1700
Data Index: 6069345 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3989. Min Act: -0.1700
Data Index: 3818570 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3833. Min Act: -0.1700
Data Index: 5931934 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3676. Min Act: -0.1700
Data Index: 2566157 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3676. Min Act: -0.1700
Data Index: 6809471 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3519. Min Act: -0.1700
Data Index: 8513744 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3362. Min Act: -0.1700
Data Index: 6831511 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3519. Min Act: -0.1700
Data Index: 2226680 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3205. Min Act: -0.1700
Data Index: 3495182 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3362. Min Act: -0.1700
Data Index: 2823661 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3048. Min Act: -0.1700
Data Index: 8664418 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.3205. Min Act: -0.1700
Data Index: 7675641 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.2891. Min Act: -0.1700
Data Index: 6333196 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.2734. Min Act: -0.1700
Data Index: 8567352 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.2891. Min Act: -0.1700
Data Index: 7447311 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.2891. Min Act: -0.1700
Data Index: 960305 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.2891. Min Act: -0.1700
Data Index: 2305252 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.2577. Min Act: -0.1700
Data Index: 8104147 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5399. Min Range: -3.5399
Max Act: 3.2420. Min Act: -0.1700
Data Index: 115406 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19