Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.3004. Min Act: -0.1700
Data Index: 8102388 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.3004. Min Act: -0.1700
Data Index: 1534988 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.2691. Min Act: -0.1700
Data Index: 7148078 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.2691. Min Act: -0.1700
Data Index: 7390674 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.2066. Min Act: -0.1700
Data Index: 484973 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.2066. Min Act: -0.1700
Data Index: 4312642 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.1441. Min Act: -0.1700
Data Index: 4072733 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.1441. Min Act: -0.1700
Data Index: 2486411 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.1441. Min Act: -0.1700
Data Index: 4469947 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0816. Min Act: -0.1700
Data Index: 2572421 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0816. Min Act: -0.1700
Data Index: 4444540 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0816. Min Act: -0.1700
Data Index: 3914104 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0504. Min Act: -0.1700
Data Index: 6347147 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0191. Min Act: -0.1700
Data Index: 3226220 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0504. Min Act: -0.1700
Data Index: 31263 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0504. Min Act: -0.1700
Data Index: 8074498 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0816. Min Act: -0.1700
Data Index: 5565928 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0191. Min Act: -0.1700
Data Index: 8631960 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0504. Min Act: -0.1700
Data Index: 3549669 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3004. Min Range: -4.3004
Max Act: 4.0191. Min Act: -0.1700
Data Index: 7701690 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19