Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.4518. Min Range: -10.4518
Max Act: 10.3893. Min Act: -0.1700
Data Index: 4305421 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4518. Min Range: -10.4518
Max Act: 10.4518. Min Act: -0.1700
Data Index: 1488506 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4518. Min Range: -10.4518
Max Act: 10.2643. Min Act: -0.1700
Data Index: 2044877 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4518. Min Range: -10.4518
Max Act: 10.0768. Min Act: -0.1700
Data Index: 7782507 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.9518. Min Act: -0.1700
Data Index: 182247 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4518. Min Range: -10.4518
Max Act: 10.0768. Min Act: -0.1700
Data Index: 3041976 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4518. Min Range: -10.4518
Max Act: 10.0143. Min Act: -0.1700
Data Index: 5236716 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.9518. Min Act: -0.1700
Data Index: 533178 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.8268. Min Act: -0.1700
Data Index: 6472411 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.8268. Min Act: -0.1700
Data Index: 2677419 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.7643. Min Act: -0.1700
Data Index: 1559727 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.7018. Min Act: -0.1700
Data Index: 46940 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.6393. Min Act: -0.1700
Data Index: 5389867 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.6393. Min Act: -0.1700
Data Index: 439549 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.6393. Min Act: -0.1700
Data Index: 7798487 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.6393. Min Act: -0.1700
Data Index: 7889755 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.5143. Min Act: -0.1700
Data Index: 3099265 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.5143. Min Act: -0.1700
Data Index: 1639072 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.4518. Min Act: -0.1700
Data Index: 2515067 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4518. Min Range: -10.4518
Max Act: 9.3893. Min Act: -0.1700
Data Index: 171156 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19