Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1070. Min Range: -7.1070
Max Act: 7.1070. Min Act: -0.1700
Data Index: 69642 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1070. Min Range: -7.1070
Max Act: 6.6070. Min Act: -0.1700
Data Index: 6430543 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1070. Min Range: -7.1070
Max Act: 6.2320. Min Act: -0.1700
Data Index: 1013754 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1070. Min Range: -7.1070
Max Act: 6.0445. Min Act: -0.1700
Data Index: 8590248 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1070. Min Range: -7.1070
Max Act: 6.0445. Min Act: -0.1700
Data Index: 5273368 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1070. Min Range: -7.1070
Max Act: 6.0132. Min Act: -0.1700
Data Index: 6569087 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1070. Min Range: -7.1070
Max Act: 6.0132. Min Act: -0.1700
Data Index: 5613611 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.9507. Min Act: -0.1700
Data Index: 2105865 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.8257. Min Act: -0.1700
Data Index: 1294224 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.8257. Min Act: -0.1700
Data Index: 3171048 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7945. Min Act: -0.1700
Data Index: 7707054 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7945. Min Act: -0.1700
Data Index: 4771070 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7632. Min Act: -0.1700
Data Index: 4266223 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7632. Min Act: -0.1700
Data Index: 1285359 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7320. Min Act: -0.1700
Data Index: 8711044 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7320. Min Act: -0.1700
Data Index: 484561 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7007. Min Act: -0.1700
Data Index: 5123872 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7007. Min Act: -0.1700
Data Index: 7148309 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7320. Min Act: -0.1700
Data Index: 3524116 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1070. Min Range: -7.1070
Max Act: 5.7007. Min Act: -0.1700
Data Index: 3570389 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19