Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.4255. Min Act: -0.1700
Data Index: 6402956 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.3020. Min Act: -0.1700
Data Index: 6735823 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2491. Min Act: -0.1700
Data Index: 2196290 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2227. Min Act: -0.1700
Data Index: 652456 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2227. Min Act: -0.1700
Data Index: 4434510 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2315. Min Act: -0.1700
Data Index: 4332541 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2227. Min Act: -0.1700
Data Index: 5372992 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2227. Min Act: -0.1700
Data Index: 7701174 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2139. Min Act: -0.1700
Data Index: 2187061 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2139. Min Act: -0.1700
Data Index: 355385 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2227. Min Act: -0.1700
Data Index: 5723493 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2051. Min Act: -0.1700
Data Index: 749528 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2227. Min Act: -0.1700
Data Index: 5372485 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.1963. Min Act: -0.1700
Data Index: 691935 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2051. Min Act: -0.1700
Data Index: 408869 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.2227. Min Act: -0.1700
Data Index: 2696158 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.1875. Min Act: -0.1700
Data Index: 1333383 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.1963. Min Act: -0.1700
Data Index: 2497885 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.1875. Min Act: -0.1700
Data Index: 6649015 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4255. Min Range: -1.4255
Max Act: 1.1963. Min Act: -0.1700
Data Index: 4736187 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19