Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0884. Min Range: -4.0884
Max Act: 4.0884. Min Act: -0.1700
Data Index: 7477657 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0884. Min Range: -4.0884
Max Act: 4.0884. Min Act: -0.1700
Data Index: 1481493 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0884. Min Range: -4.0884
Max Act: 4.0259. Min Act: -0.1700
Data Index: 4753718 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0884. Min Range: -4.0884
Max Act: 4.0259. Min Act: -0.1700
Data Index: 8654559 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.9946. Min Act: -0.1700
Data Index: 4727383 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.9321. Min Act: -0.1700
Data Index: 7157799 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.9321. Min Act: -0.1700
Data Index: 3543229 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.9008. Min Act: -0.1700
Data Index: 4306335 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8695. Min Act: -0.1700
Data Index: 430935 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8695. Min Act: -0.1700
Data Index: 6284708 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8695. Min Act: -0.1700
Data Index: 2700798 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8383. Min Act: -0.1700
Data Index: 6308141 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8695. Min Act: -0.1700
Data Index: 1640724 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8070. Min Act: -0.1700
Data Index: 1481498 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8383. Min Act: -0.1700
Data Index: 6516317 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8383. Min Act: -0.1700
Data Index: 3579250 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8383. Min Act: -0.1700
Data Index: 4175410 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8383. Min Act: -0.1700
Data Index: 3813419 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8070. Min Act: -0.1700
Data Index: 4110531 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0884. Min Range: -4.0884
Max Act: 3.8070. Min Act: -0.1700
Data Index: 3522647 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19