Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2119 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5682. Min Range: -7.5682
Max Act: 7.5682. Min Act: -0.1700
Data Index: 7427058 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5682. Min Range: -7.5682
Max Act: 7.2244. Min Act: -0.1700
Data Index: 239206 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5682. Min Range: -7.5682
Max Act: 7.1619. Min Act: -0.1700
Data Index: 8432556 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5682. Min Range: -7.5682
Max Act: 7.0994. Min Act: -0.1700
Data Index: 6572908 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5682. Min Range: -7.5682
Max Act: 7.0369. Min Act: -0.1700
Data Index: 7073017 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.9432. Min Act: -0.1700
Data Index: 5877421 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.9432. Min Act: -0.1700
Data Index: 5470382 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.9432. Min Act: -0.1700
Data Index: 3398761 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.9432. Min Act: -0.1700
Data Index: 5004657 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.9119. Min Act: -0.1700
Data Index: 3366470 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.9119. Min Act: -0.1700
Data Index: 3001747 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.8807. Min Act: -0.1700
Data Index: 6606917 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.8494. Min Act: -0.1700
Data Index: 7646204 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.8494. Min Act: -0.1700
Data Index: 3998082 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.8182. Min Act: -0.1700
Data Index: 8599412 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.7869. Min Act: -0.1700
Data Index: 32388 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.7869. Min Act: -0.1700
Data Index: 8604824 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.7244. Min Act: -0.1700
Data Index: 5079984 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.7244. Min Act: -0.1700
Data Index: 6080560 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5682. Min Range: -7.5682
Max Act: 6.6619. Min Act: -0.1700
Data Index: 6875440 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19