Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1671 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1632. Min Range: -5.1632
Max Act: 5.1632. Min Act: -0.1700
Data Index: 1522316 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1632. Min Range: -5.1632
Max Act: 5.1320. Min Act: -0.1700
Data Index: 3119466 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1632. Min Range: -5.1632
Max Act: 5.0695. Min Act: -0.1700
Data Index: 8811426 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1632. Min Range: -5.1632
Max Act: 5.0695. Min Act: -0.1700
Data Index: 3383351 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9757. Min Act: -0.1700
Data Index: 2004454 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1632. Min Range: -5.1632
Max Act: 5.0070. Min Act: -0.1700
Data Index: 2505483 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9757. Min Act: -0.1700
Data Index: 3149761 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9757. Min Act: -0.1700
Data Index: 8803203 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9757. Min Act: -0.1700
Data Index: 3663295 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9445. Min Act: -0.1700
Data Index: 7608759 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9445. Min Act: -0.1700
Data Index: 415527 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9445. Min Act: -0.1700
Data Index: 6736782 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9445. Min Act: -0.1694
Data Index: 5682145 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9132. Min Act: -0.1700
Data Index: 6381955 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9132. Min Act: -0.1700
Data Index: 1697803 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9132. Min Act: -0.1700
Data Index: 6359054 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9132. Min Act: -0.1700
Data Index: 4818056 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.8820. Min Act: -0.1700
Data Index: 1721165 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.8507. Min Act: -0.1700
Data Index: 3119468 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1632. Min Range: -5.1632
Max Act: 4.9132. Min Act: -0.1700
Data Index: 6455040 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19