Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 523 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.4387. Min Act: -0.1700
Data Index: 8683857 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3917. Min Act: -0.1700
Data Index: 6940569 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.4073. Min Act: -0.1700
Data Index: 6247386 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.4073. Min Act: -0.1700
Data Index: 5371137 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3917. Min Act: -0.1700
Data Index: 2525037 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.4073. Min Act: -0.1700
Data Index: 7508943 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3917. Min Act: -0.1700
Data Index: 6798493 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3760. Min Act: -0.1700
Data Index: 2186044 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3760. Min Act: -0.1700
Data Index: 7814967 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3603. Min Act: -0.1700
Data Index: 6649288 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3603. Min Act: -0.1700
Data Index: 1054366 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3446. Min Act: -0.1700
Data Index: 4299331 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3446. Min Act: -0.1700
Data Index: 3988090 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.2975. Min Act: -0.1700
Data Index: 7433892 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3446. Min Act: -0.1700
Data Index: 3629210 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3446. Min Act: -0.1700
Data Index: 4153998 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3289. Min Act: -0.1700
Data Index: 5003520 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3446. Min Act: -0.1700
Data Index: 7924633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3446. Min Act: -0.1700
Data Index: 6932719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.3132. Min Act: -0.1700
Data Index: 5205540 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19