Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.6985. Min Act: -0.1700
Data Index: 969851 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.5110. Min Act: -0.1700
Data Index: 1671940 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.4798. Min Act: -0.1700
Data Index: 1937461 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.3548. Min Act: -0.1700
Data Index: 7240194 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.3235. Min Act: -0.1700
Data Index: 4142043 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.3235. Min Act: -0.1700
Data Index: 6323038 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.3235. Min Act: -0.1700
Data Index: 4849910 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.2610. Min Act: -0.1700
Data Index: 4008391 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.2297. Min Act: -0.1700
Data Index: 6596648 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.2297. Min Act: -0.1700
Data Index: 120270 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1985. Min Act: -0.1700
Data Index: 4940001 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1985. Min Act: -0.1700
Data Index: 8403991 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1985. Min Act: -0.1700
Data Index: 4115988 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1672. Min Act: -0.1700
Data Index: 3315254 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1672. Min Act: -0.1700
Data Index: 1181550 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1672. Min Act: -0.1700
Data Index: 920882 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1672. Min Act: -0.1700
Data Index: 1148053 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1672. Min Act: -0.1700
Data Index: 4903439 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1360. Min Act: -0.1700
Data Index: 1052946 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6985. Min Range: -4.6985
Max Act: 4.1360. Min Act: -0.1700
Data Index: 6178487 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19