Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 245 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.6086. Min Act: -0.1700
Data Index: 1097362 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5925. Min Act: -0.1700
Data Index: 8291654 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5925. Min Act: -0.1700
Data Index: 5220611 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5764. Min Act: -0.1700
Data Index: 1313204 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5602. Min Act: -0.1700
Data Index: 5791601 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5602. Min Act: -0.1700
Data Index: 4671757 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5602. Min Act: -0.1700
Data Index: 7423590 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5441. Min Act: -0.1700
Data Index: 1131961 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5441. Min Act: -0.1700
Data Index: 4425275 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5602. Min Act: -0.1700
Data Index: 5920243 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5602. Min Act: -0.1700
Data Index: 5190109 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5602. Min Act: -0.1700
Data Index: 7846941 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5441. Min Act: -0.1700
Data Index: 2368395 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5279. Min Act: -0.1700
Data Index: 1863707 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5279. Min Act: -0.1700
Data Index: 5595166 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5279. Min Act: -0.1700
Data Index: 4078302 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5279. Min Act: -0.1700
Data Index: 232731 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5441. Min Act: -0.1700
Data Index: 2306996 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5118. Min Act: -0.1700
Data Index: 4480892 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6086. Min Range: -2.6086
Max Act: 2.5441. Min Act: -0.1700
Data Index: 5561733 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19