Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.3987. Min Act: -0.1700
Data Index: 297223 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.1316. Min Act: -0.1700
Data Index: 5894214 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.1159. Min Act: -0.1700
Data Index: 4709333 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.1159. Min Act: -0.1700
Data Index: 8158066 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.1001. Min Act: -0.1700
Data Index: 5778476 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0686. Min Act: -0.1700
Data Index: 5727755 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0528. Min Act: -0.1700
Data Index: 8067956 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0528. Min Act: -0.1700
Data Index: 5138705 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0213. Min Act: -0.1700
Data Index: 1649518 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0213. Min Act: -0.1700
Data Index: 5866733 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0055. Min Act: -0.1700
Data Index: 8519422 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0370. Min Act: -0.1700
Data Index: 7277187 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0213. Min Act: -0.1700
Data Index: 2158063 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0213. Min Act: -0.1700
Data Index: 3665217 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3987. Min Range: -3.3987
Max Act: 3.0055. Min Act: -0.1700
Data Index: 689121 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3987. Min Range: -3.3987
Max Act: 2.9897. Min Act: -0.1700
Data Index: 6837320 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3987. Min Range: -3.3987
Max Act: 2.9738. Min Act: -0.1700
Data Index: 2673379 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3987. Min Range: -3.3987
Max Act: 2.9897. Min Act: -0.1700
Data Index: 2099291 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3987. Min Range: -3.3987
Max Act: 2.9738. Min Act: -0.1700
Data Index: 774641 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3987. Min Range: -3.3987
Max Act: 2.9897. Min Act: -0.1700
Data Index: 2870214 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19