Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.3632. Min Act: -0.1700
Data Index: 5049768 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.3007. Min Act: -0.1700
Data Index: 2066399 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.2069. Min Act: -0.1700
Data Index: 5714998 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.2382. Min Act: -0.1700
Data Index: 1801156 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.1757. Min Act: -0.1700
Data Index: 5598516 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.1444. Min Act: -0.1700
Data Index: 7411618 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.1444. Min Act: -0.1700
Data Index: 1315634 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.0819. Min Act: -0.1700
Data Index: 3970020 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.0819. Min Act: -0.1700
Data Index: 8445580 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.0507. Min Act: -0.1700
Data Index: 1975054 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.0507. Min Act: -0.1700
Data Index: 3625434 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.0194. Min Act: -0.1700
Data Index: 4941110 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.0194. Min Act: -0.1700
Data Index: 2656319 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3632. Min Range: -6.3632
Max Act: 6.0194. Min Act: -0.1700
Data Index: 7821465 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3632. Min Range: -6.3632
Max Act: 5.9569. Min Act: -0.1700
Data Index: 6600435 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3632. Min Range: -6.3632
Max Act: 5.9569. Min Act: -0.1700
Data Index: 1297547 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3632. Min Range: -6.3632
Max Act: 5.9569. Min Act: -0.1700
Data Index: 2066397 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3632. Min Range: -6.3632
Max Act: 5.9569. Min Act: -0.1700
Data Index: 4134747 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3632. Min Range: -6.3632
Max Act: 5.8944. Min Act: -0.1700
Data Index: 5943280 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3632. Min Range: -6.3632
Max Act: 5.9257. Min Act: -0.1700
Data Index: 2253825 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19