Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.2824. Min Act: -0.1700
Data Index: 8413131 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.2511. Min Act: -0.1700
Data Index: 6198882 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.1574. Min Act: -0.1700
Data Index: 2775010 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.1574. Min Act: -0.1700
Data Index: 2844490 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.1261. Min Act: -0.1700
Data Index: 3035182 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0949. Min Act: -0.1700
Data Index: 615953 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0324. Min Act: -0.1700
Data Index: 2343581 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0324. Min Act: -0.1700
Data Index: 1285260 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0324. Min Act: -0.1700
Data Index: 7391788 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0011. Min Act: -0.1700
Data Index: 5103486 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0011. Min Act: -0.1700
Data Index: 242545 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.9699. Min Act: -0.1700
Data Index: 4360271 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.9699. Min Act: -0.1700
Data Index: 7011394 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.9386. Min Act: -0.1700
Data Index: 2812457 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.9699. Min Act: -0.1700
Data Index: 5228638 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.9699. Min Act: -0.1700
Data Index: 3231092 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.9386. Min Act: -0.1700
Data Index: 2132309 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.9386. Min Act: -0.1700
Data Index: 8387557 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.9074. Min Act: -0.1700
Data Index: 6092052 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2824. Min Range: -5.2824
Max Act: 4.8761. Min Act: -0.1700
Data Index: 2888580 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19