Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.7622. Min Act: -0.1700
Data Index: 6601824 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.6997. Min Act: -0.1700
Data Index: 4533214 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.6060. Min Act: -0.1700
Data Index: 5325388 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.5747. Min Act: -0.1700
Data Index: 6966521 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.3872. Min Act: -0.1700
Data Index: 4625641 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.2935. Min Act: -0.1700
Data Index: 7180418 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.3247. Min Act: -0.1700
Data Index: 6926664 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.2935. Min Act: -0.1700
Data Index: 4920157 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.2935. Min Act: -0.1700
Data Index: 4590507 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.2310. Min Act: -0.1700
Data Index: 251693 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.1685. Min Act: -0.1700
Data Index: 7880233 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.1372. Min Act: -0.1700
Data Index: 524483 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.1060. Min Act: -0.1700
Data Index: 7342384 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.1060. Min Act: -0.1700
Data Index: 7667235 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.0435. Min Act: -0.1700
Data Index: 1160890 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.0747. Min Act: -0.1700
Data Index: 8262166 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.0122. Min Act: -0.1700
Data Index: 5157861 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.0435. Min Act: -0.1700
Data Index: 7539185 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.0122. Min Act: -0.1700
Data Index: 1031940 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7622. Min Range: -6.7622
Max Act: 6.0122. Min Act: -0.1700
Data Index: 8336540 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19