Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.5082. Min Act: -0.1700
Data Index: 643835 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.1957. Min Act: -0.1700
Data Index: 2448198 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.1957. Min Act: -0.1700
Data Index: 1128564 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.1332. Min Act: -0.1700
Data Index: 446138 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.1332. Min Act: -0.1700
Data Index: 5325849 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.0707. Min Act: -0.1700
Data Index: 543714 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.0082. Min Act: -0.1700
Data Index: 4050843 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.0082. Min Act: -0.1700
Data Index: 1084443 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5082. Min Range: -7.5082
Max Act: 7.0082. Min Act: -0.1700
Data Index: 3919307 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.9457. Min Act: -0.1700
Data Index: 8647243 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.9457. Min Act: -0.1700
Data Index: 2551 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.9144. Min Act: -0.1700
Data Index: 8631123 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.9144. Min Act: -0.1700
Data Index: 1060323 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.9144. Min Act: -0.1700
Data Index: 5820127 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.9144. Min Act: -0.1700
Data Index: 157620 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.8832. Min Act: -0.1700
Data Index: 731453 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.8519. Min Act: -0.1700
Data Index: 1894472 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.8519. Min Act: -0.1700
Data Index: 4696332 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.8519. Min Act: -0.1700
Data Index: 4010793 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5082. Min Range: -7.5082
Max Act: 6.8519. Min Act: -0.1700
Data Index: 2685579 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19