Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0325. Min Range: -6.0325
Max Act: 6.0325. Min Act: -0.1700
Data Index: 1032315 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0325. Min Range: -6.0325
Max Act: 6.0013. Min Act: -0.1700
Data Index: 5383816 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.9700. Min Act: -0.1700
Data Index: 7807823 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8763. Min Act: -0.1700
Data Index: 6773852 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8450. Min Act: -0.1700
Data Index: 1384466 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8450. Min Act: -0.1700
Data Index: 1873019 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8450. Min Act: -0.1700
Data Index: 7092377 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8450. Min Act: -0.1700
Data Index: 8323675 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8450. Min Act: -0.1700
Data Index: 1685122 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8450. Min Act: -0.1700
Data Index: 6484192 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8138. Min Act: -0.1700
Data Index: 7233592 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8138. Min Act: -0.1700
Data Index: 3010895 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8138. Min Act: -0.1700
Data Index: 5048930 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.7825. Min Act: -0.1700
Data Index: 6677625 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.7825. Min Act: -0.1700
Data Index: 6118779 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.7825. Min Act: -0.1700
Data Index: 7340319 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.7513. Min Act: -0.1700
Data Index: 3251662 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.7513. Min Act: -0.1700
Data Index: 2087476 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.8138. Min Act: -0.1700
Data Index: 8262373 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0325. Min Range: -6.0325
Max Act: 5.7825. Min Act: -0.1700
Data Index: 611528 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19