Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.9418. Min Act: -0.1700
Data Index: 5589721 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8168. Min Act: -0.1700
Data Index: 1127511 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8480. Min Act: -0.1700
Data Index: 2939783 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8168. Min Act: -0.1700
Data Index: 4920865 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8480. Min Act: -0.1700
Data Index: 2400546 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8480. Min Act: -0.1700
Data Index: 42320 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7855. Min Act: -0.1700
Data Index: 5026993 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8168. Min Act: -0.1700
Data Index: 5420107 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8480. Min Act: -0.1700
Data Index: 6958023 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8480. Min Act: -0.1700
Data Index: 4994951 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8168. Min Act: -0.1700
Data Index: 95683 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7855. Min Act: -0.1700
Data Index: 1629348 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7542. Min Act: -0.1700
Data Index: 4515377 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7855. Min Act: -0.1700
Data Index: 4662480 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7855. Min Act: -0.1700
Data Index: 2694776 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7855. Min Act: -0.1700
Data Index: 4622 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7855. Min Act: -0.1700
Data Index: 3914825 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7855. Min Act: -0.1700
Data Index: 3255905 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.8168. Min Act: -0.1700
Data Index: 1835938 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9418. Min Range: -3.9418
Max Act: 3.7542. Min Act: -0.1700
Data Index: 3213450 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19