Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2751 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.5276. Min Act: -0.1688
Data Index: 7976618 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.4952. Min Act: -0.1700
Data Index: 5063640 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.4302. Min Act: -0.1700
Data Index: 2867733 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.4140. Min Act: -0.1690
Data Index: 2867744 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3976. Min Act: -0.1700
Data Index: 4895286 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3813. Min Act: -0.1700
Data Index: 8450514 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3813. Min Act: -0.1700
Data Index: 3187064 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3813. Min Act: -0.1700
Data Index: 7105653 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3813. Min Act: -0.1700
Data Index: 4556734 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3650. Min Act: -0.1700
Data Index: 5430533 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3486. Min Act: -0.1700
Data Index: 6052348 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3486. Min Act: -0.1700
Data Index: 2645423 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3650. Min Act: -0.1699
Data Index: 4468507 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3650. Min Act: -0.1700
Data Index: 2279259 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3813. Min Act: -0.1700
Data Index: 3152781 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3486. Min Act: -0.1700
Data Index: 8055454 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3650. Min Act: -0.1699
Data Index: 2400570 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3322. Min Act: -0.1700
Data Index: 1926969 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3486. Min Act: -0.1700
Data Index: 3154325 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5276. Min Range: -2.5276
Max Act: 2.3486. Min Act: -0.1700
Data Index: 3073 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19