Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3455. Min Range: -9.3455
Max Act: 9.3455. Min Act: -0.1700
Data Index: 1097666 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3455. Min Range: -9.3455
Max Act: 9.0330. Min Act: -0.1700
Data Index: 4520109 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3455. Min Range: -9.3455
Max Act: 9.1580. Min Act: -0.1700
Data Index: 990782 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3455. Min Range: -9.3455
Max Act: 9.0330. Min Act: -0.1700
Data Index: 5550890 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3455. Min Range: -9.3455
Max Act: 9.0330. Min Act: -0.1700
Data Index: 5480959 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.9705. Min Act: -0.1700
Data Index: 8506051 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.9080. Min Act: -0.1700
Data Index: 498510 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.8455. Min Act: -0.1700
Data Index: 498512 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.8455. Min Act: -0.1700
Data Index: 7076718 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.6580. Min Act: -0.1700
Data Index: 4923400 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.6580. Min Act: -0.1700
Data Index: 7941974 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.5955. Min Act: -0.1700
Data Index: 7815475 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.5330. Min Act: -0.1700
Data Index: 2772887 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.4705. Min Act: -0.1700
Data Index: 5741509 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.4705. Min Act: -0.1700
Data Index: 5052256 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.4080. Min Act: -0.1700
Data Index: 5909003 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.4080. Min Act: -0.1700
Data Index: 7273537 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.4080. Min Act: -0.1700
Data Index: 7500218 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.4080. Min Act: -0.1700
Data Index: 510616 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3455. Min Range: -9.3455
Max Act: 8.3455. Min Act: -0.1700
Data Index: 1668024 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19