Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1212. Min Range: -3.1212
Max Act: 3.1212. Min Act: -0.1700
Data Index: 1873880 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1212. Min Range: -3.1212
Max Act: 3.0266. Min Act: -0.1700
Data Index: 8025064 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.9792. Min Act: -0.1700
Data Index: 4035467 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.9792. Min Act: -0.1700
Data Index: 2831705 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.9317. Min Act: -0.1700
Data Index: 1983394 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.9159. Min Act: -0.1700
Data Index: 4651559 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8842. Min Act: -0.1700
Data Index: 744502 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8842. Min Act: -0.1700
Data Index: 2689712 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8365. Min Act: -0.1700
Data Index: 6080924 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8683. Min Act: -0.1700
Data Index: 7666307 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8365. Min Act: -0.1700
Data Index: 4974459 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8524. Min Act: -0.1700
Data Index: 8264298 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8206. Min Act: -0.1700
Data Index: 4337098 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8047. Min Act: -0.1700
Data Index: 8670590 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8365. Min Act: -0.1700
Data Index: 965073 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8047. Min Act: -0.1700
Data Index: 6754129 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8206. Min Act: -0.1700
Data Index: 2076294 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.7888. Min Act: -0.1700
Data Index: 4477949 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.7888. Min Act: -0.1700
Data Index: 4277072 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1212. Min Range: -3.1212
Max Act: 2.8047. Min Act: -0.1700
Data Index: 3843138 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19