Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 646 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.8157. Min Act: -0.1700
Data Index: 5270597 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.8157. Min Act: -0.1700
Data Index: 8002200 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6905. Min Act: -0.1700
Data Index: 1226193 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6593. Min Act: -0.1700
Data Index: 6213899 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6593. Min Act: -0.1700
Data Index: 7498417 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6905. Min Act: -0.1700
Data Index: 3957391 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6593. Min Act: -0.1700
Data Index: 4249321 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6593. Min Act: -0.1700
Data Index: 5992133 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6593. Min Act: -0.1700
Data Index: 2554512 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6280. Min Act: -0.1700
Data Index: 4668180 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6280. Min Act: -0.1700
Data Index: 2870941 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.5967. Min Act: -0.1700
Data Index: 6831787 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.6280. Min Act: -0.1700
Data Index: 3929450 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.5967. Min Act: -0.1700
Data Index: 8691981 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.5967. Min Act: -0.1700
Data Index: 594124 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.5967. Min Act: -0.1700
Data Index: 2932188 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.5967. Min Act: -0.1700
Data Index: 8583601 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.5654. Min Act: -0.1700
Data Index: 4239085 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.5654. Min Act: -0.1700
Data Index: 636892 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8157. Min Range: -3.8157
Max Act: 3.5654. Min Act: -0.1700
Data Index: 420581 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19