Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 744 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3919. Min Range: -7.3919
Max Act: 7.3919. Min Act: -0.1700
Data Index: 3255996 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3919. Min Range: -7.3919
Max Act: 7.3607. Min Act: -0.1700
Data Index: 4431847 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3919. Min Range: -7.3919
Max Act: 7.2044. Min Act: -0.1700
Data Index: 1132922 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3919. Min Range: -7.3919
Max Act: 7.1732. Min Act: -0.1700
Data Index: 3987004 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3919. Min Range: -7.3919
Max Act: 7.1107. Min Act: -0.1700
Data Index: 3180051 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3919. Min Range: -7.3919
Max Act: 7.0794. Min Act: -0.1700
Data Index: 4451671 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3919. Min Range: -7.3919
Max Act: 7.0482. Min Act: -0.1700
Data Index: 740688 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3919. Min Range: -7.3919
Max Act: 7.0169. Min Act: -0.1700
Data Index: 7736042 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9857. Min Act: -0.1700
Data Index: 7473379 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9857. Min Act: -0.1700
Data Index: 6541962 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9857. Min Act: -0.1700
Data Index: 4907464 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9857. Min Act: -0.1700
Data Index: 6866638 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9544. Min Act: -0.1700
Data Index: 6457260 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9544. Min Act: -0.1700
Data Index: 7973476 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9544. Min Act: -0.1700
Data Index: 3982053 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9544. Min Act: -0.1700
Data Index: 2680218 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9544. Min Act: -0.1700
Data Index: 7201681 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9544. Min Act: -0.1700
Data Index: 2575100 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9232. Min Act: -0.1700
Data Index: 2932943 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3919. Min Range: -7.3919
Max Act: 6.9232. Min Act: -0.1700
Data Index: 1798418 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19