Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.3249. Min Act: -0.1700
Data Index: 4534480 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.2936. Min Act: -0.1700
Data Index: 4789445 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.2624. Min Act: -0.1700
Data Index: 5631983 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.1999. Min Act: -0.1700
Data Index: 5469621 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.1686. Min Act: -0.1700
Data Index: 44143 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.1686. Min Act: -0.1700
Data Index: 5087832 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.1374. Min Act: -0.1700
Data Index: 267815 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.1374. Min Act: -0.1700
Data Index: 790825 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.1061. Min Act: -0.1700
Data Index: 7725218 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.0749. Min Act: -0.1700
Data Index: 4085838 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.0436. Min Act: -0.1700
Data Index: 4121952 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.0436. Min Act: -0.1700
Data Index: 1185657 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.0124. Min Act: -0.1700
Data Index: 6136423 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.0436. Min Act: -0.1700
Data Index: 6976022 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3249. Min Range: -6.3249
Max Act: 6.0124. Min Act: -0.1700
Data Index: 3729191 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3249. Min Range: -6.3249
Max Act: 5.9811. Min Act: -0.1700
Data Index: 7992333 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3249. Min Range: -6.3249
Max Act: 5.9811. Min Act: -0.1700
Data Index: 7148540 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3249. Min Range: -6.3249
Max Act: 5.9811. Min Act: -0.1700
Data Index: 5821254 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3249. Min Range: -6.3249
Max Act: 5.9499. Min Act: -0.1700
Data Index: 756025 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3249. Min Range: -6.3249
Max Act: 5.9499. Min Act: -0.1700
Data Index: 6235023 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19