Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.7224. Min Act: -0.1700
Data Index: 2741550 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.4724. Min Act: -0.1700
Data Index: 2488437 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.4724. Min Act: -0.1700
Data Index: 8213102 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.4412. Min Act: -0.1700
Data Index: 3040539 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.4099. Min Act: -0.1700
Data Index: 4740549 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.3162. Min Act: -0.1700
Data Index: 139920 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.2849. Min Act: -0.1700
Data Index: 6706567 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.1912. Min Act: -0.1700
Data Index: 8388648 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.1599. Min Act: -0.1700
Data Index: 279637 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.1287. Min Act: -0.1700
Data Index: 7219341 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.0662. Min Act: -0.1700
Data Index: 4794512 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.0974. Min Act: -0.1700
Data Index: 2412086 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.0349. Min Act: -0.1700
Data Index: 5131019 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7224. Min Range: -7.7224
Max Act: 7.0037. Min Act: -0.1700
Data Index: 3854748 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7224. Min Range: -7.7224
Max Act: 6.9724. Min Act: -0.1700
Data Index: 2429237 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7224. Min Range: -7.7224
Max Act: 6.9724. Min Act: -0.1700
Data Index: 3978887 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7224. Min Range: -7.7224
Max Act: 6.9412. Min Act: -0.1700
Data Index: 5475849 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7224. Min Range: -7.7224
Max Act: 6.9724. Min Act: -0.1700
Data Index: 4719144 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7224. Min Range: -7.7224
Max Act: 6.9412. Min Act: -0.1700
Data Index: 1123768 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7224. Min Range: -7.7224
Max Act: 6.9412. Min Act: -0.1700
Data Index: 3678896 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19