Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5183 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.4827. Min Act: -0.1700
Data Index: 7106002 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.4513. Min Act: -0.1700
Data Index: 2725529 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3886. Min Act: -0.1700
Data Index: 6641717 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3886. Min Act: -0.1700
Data Index: 3731914 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3729. Min Act: -0.1700
Data Index: 465273 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3729. Min Act: -0.1700
Data Index: 858958 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3729. Min Act: -0.1700
Data Index: 2647946 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3416. Min Act: -0.1700
Data Index: 6295127 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3416. Min Act: -0.1700
Data Index: 1323347 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3416. Min Act: -0.1700
Data Index: 5593225 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3259. Min Act: -0.1700
Data Index: 779203 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3259. Min Act: -0.1700
Data Index: 3704320 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3259. Min Act: -0.1700
Data Index: 3442698 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3259. Min Act: -0.1700
Data Index: 8300012 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.3259. Min Act: -0.1700
Data Index: 2612127 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.2945. Min Act: -0.1700
Data Index: 5581957 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.2788. Min Act: -0.1700
Data Index: 2365752 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.2945. Min Act: -0.1700
Data Index: 3371342 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.2788. Min Act: -0.1700
Data Index: 8369441 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4827. Min Range: -3.4827
Max Act: 3.2788. Min Act: -0.1700
Data Index: 1301481 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19