Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.6903. Min Act: -0.1700
Data Index: 8670033 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.6746. Min Act: -0.1700
Data Index: 4663641 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1233619 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.5181. Min Act: -0.1700
Data Index: 6843777 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.4711. Min Act: -0.1700
Data Index: 2724337 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.4398. Min Act: -0.1700
Data Index: 3021728 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3927. Min Act: -0.1700
Data Index: 6490311 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3771. Min Act: -0.1700
Data Index: 5091049 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3614. Min Act: -0.1700
Data Index: 2779066 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3614. Min Act: -0.1700
Data Index: 6214605 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3457. Min Act: -0.1700
Data Index: 1798351 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3300. Min Act: -0.1700
Data Index: 6755596 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3143. Min Act: -0.1700
Data Index: 623467 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3300. Min Act: -0.1700
Data Index: 7088781 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3143. Min Act: -0.1700
Data Index: 856856 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.2986. Min Act: -0.1700
Data Index: 7338775 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.2986. Min Act: -0.1700
Data Index: 4580029 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.2986. Min Act: -0.1700
Data Index: 6507655 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.3143. Min Act: -0.1700
Data Index: 1001311 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6903. Min Range: -3.6903
Max Act: 3.2986. Min Act: -0.1700
Data Index: 3779312 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19