Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 586 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.7457. Min Act: -0.1700
Data Index: 8735500 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.7144. Min Act: -0.1700
Data Index: 1680890 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6832. Min Act: -0.1700
Data Index: 8579671 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6832. Min Act: -0.1700
Data Index: 1402542 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6832. Min Act: -0.1700
Data Index: 7049367 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6519. Min Act: -0.1700
Data Index: 1465233 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6519. Min Act: -0.1700
Data Index: 2595857 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6519. Min Act: -0.1700
Data Index: 4962051 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6519. Min Act: -0.1700
Data Index: 6018856 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6207. Min Act: -0.1700
Data Index: 6443388 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6207. Min Act: -0.1700
Data Index: 3112357 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.6207. Min Act: -0.1700
Data Index: 6451129 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.5894. Min Act: -0.1700
Data Index: 1956319 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.5894. Min Act: -0.1700
Data Index: 7988116 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.5269. Min Act: -0.1700
Data Index: 3004697 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.5269. Min Act: -0.1700
Data Index: 7390941 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.4957. Min Act: -0.1700
Data Index: 7422344 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.5269. Min Act: -0.1700
Data Index: 8160306 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.5269. Min Act: -0.1700
Data Index: 2875104 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7457. Min Range: -5.7457
Max Act: 5.4957. Min Act: -0.1700
Data Index: 2179281 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19