Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 397 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.7980. Min Act: -0.1700
Data Index: 6869652 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.7355. Min Act: -0.1700
Data Index: 8806843 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.7355. Min Act: -0.1700
Data Index: 3391178 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.7043. Min Act: -0.1700
Data Index: 6083607 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.6730. Min Act: -0.1700
Data Index: 1244959 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.7043. Min Act: -0.1700
Data Index: 8539709 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.6105. Min Act: -0.1700
Data Index: 7385852 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.6105. Min Act: -0.1700
Data Index: 3548596 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.5793. Min Act: -0.1700
Data Index: 8814496 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.5793. Min Act: -0.1700
Data Index: 2421180 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.5793. Min Act: -0.1700
Data Index: 3494022 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.5168. Min Act: -0.1700
Data Index: 8092375 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.5480. Min Act: -0.1700
Data Index: 4207585 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.5168. Min Act: -0.1700
Data Index: 7391211 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.4855. Min Act: -0.1700
Data Index: 8001539 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.4855. Min Act: -0.1700
Data Index: 829664 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.4230. Min Act: -0.1700
Data Index: 1255374 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.4230. Min Act: -0.1700
Data Index: 1540232 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.4230. Min Act: -0.1700
Data Index: 3883975 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7980. Min Range: -4.7980
Max Act: 4.4230. Min Act: -0.1700
Data Index: 3911993 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19