Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2203 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.3760. Min Act: -0.1700
Data Index: 4674478 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.3760. Min Act: -0.1700
Data Index: 2748460 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.2509. Min Act: -0.1700
Data Index: 808939 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.2197. Min Act: -0.1700
Data Index: 4131738 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.2197. Min Act: -0.1700
Data Index: 5306765 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.2509. Min Act: -0.1700
Data Index: 3529125 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1884. Min Act: -0.1700
Data Index: 3999419 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1884. Min Act: -0.1700
Data Index: 6202503 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.2197. Min Act: -0.1700
Data Index: 4822319 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.2197. Min Act: -0.1700
Data Index: 2963410 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1884. Min Act: -0.1700
Data Index: 3488861 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1572. Min Act: -0.1700
Data Index: 7789250 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1572. Min Act: -0.1700
Data Index: 8289618 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1572. Min Act: -0.1700
Data Index: 2148917 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1259. Min Act: -0.1700
Data Index: 192402 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.0947. Min Act: -0.1700
Data Index: 5645695 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1259. Min Act: -0.1700
Data Index: 6248160 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1259. Min Act: -0.1700
Data Index: 6405333 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.0947. Min Act: -0.1700
Data Index: 5230898 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3760. Min Range: -4.3760
Max Act: 4.1259. Min Act: -0.1700
Data Index: 1078300 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19