Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.6945. Min Act: -0.1700
Data Index: 7667342 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.6320. Min Act: -0.1700
Data Index: 3574272 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.5382. Min Act: -0.1700
Data Index: 3135223 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.5070. Min Act: -0.1700
Data Index: 1957972 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.5382. Min Act: -0.1700
Data Index: 5616033 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.5070. Min Act: -0.1700
Data Index: 3780211 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.4757. Min Act: -0.1700
Data Index: 1309846 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.4445. Min Act: -0.1700
Data Index: 4089912 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.3820. Min Act: -0.1700
Data Index: 5035213 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.3507. Min Act: -0.1700
Data Index: 5640960 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.3507. Min Act: -0.1700
Data Index: 2307725 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.3507. Min Act: -0.1700
Data Index: 850003 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.2570. Min Act: -0.1700
Data Index: 4617199 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.2882. Min Act: -0.1700
Data Index: 8684421 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.2570. Min Act: -0.1700
Data Index: 364810 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.2257. Min Act: -0.1700
Data Index: 7704027 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.2257. Min Act: -0.1700
Data Index: 2271159 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.2570. Min Act: -0.1700
Data Index: 1720735 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.2570. Min Act: -0.1700
Data Index: 6182014 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6945. Min Range: -6.6945
Max Act: 6.2257. Min Act: -0.1700
Data Index: 1943057 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19