Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4258 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.3950. Min Act: -0.1700
Data Index: 4972719 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.2700. Min Act: -0.1700
Data Index: 4429788 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.2700. Min Act: -0.1700
Data Index: 4723589 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.2075. Min Act: -0.1700
Data Index: 3217742 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.1763. Min Act: -0.1700
Data Index: 1358517 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.1138. Min Act: -0.1700
Data Index: 905274 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.1450. Min Act: -0.1700
Data Index: 5492223 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.1450. Min Act: -0.1700
Data Index: 6657977 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.1138. Min Act: -0.1700
Data Index: 1501437 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.1138. Min Act: -0.1700
Data Index: 8613068 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.1138. Min Act: -0.1700
Data Index: 4537837 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.0200. Min Act: -0.1700
Data Index: 888880 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3950. Min Range: -5.3950
Max Act: 4.9888. Min Act: -0.1700
Data Index: 2183612 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3950. Min Range: -5.3950
Max Act: 4.9888. Min Act: -0.1700
Data Index: 8038556 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3950. Min Range: -5.3950
Max Act: 4.9888. Min Act: -0.1700
Data Index: 2932711 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3950. Min Range: -5.3950
Max Act: 4.9888. Min Act: -0.1700
Data Index: 4275880 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3950. Min Range: -5.3950
Max Act: 5.0200. Min Act: -0.1700
Data Index: 606550 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3950. Min Range: -5.3950
Max Act: 4.9575. Min Act: -0.1700
Data Index: 2111959 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3950. Min Range: -5.3950
Max Act: 4.9575. Min Act: -0.1700
Data Index: 6712576 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3950. Min Range: -5.3950
Max Act: 4.9575. Min Act: -0.1700
Data Index: 3444013 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19