Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6342 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.7763. Min Act: -0.1700
Data Index: 8295129 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.7138. Min Act: -0.1700
Data Index: 2002823 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.6513. Min Act: -0.1700
Data Index: 7434439 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.6513. Min Act: -0.1700
Data Index: 1475416 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.5888. Min Act: -0.1700
Data Index: 7364620 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.5888. Min Act: -0.1700
Data Index: 5088198 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.5263. Min Act: -0.1700
Data Index: 1408663 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4638. Min Act: -0.1700
Data Index: 3635248 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4638. Min Act: -0.1700
Data Index: 1775190 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4638. Min Act: -0.1700
Data Index: 4078430 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4638. Min Act: -0.1700
Data Index: 5026047 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4638. Min Act: -0.1700
Data Index: 8481122 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4013. Min Act: -0.1700
Data Index: 3785788 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4013. Min Act: -0.1700
Data Index: 2539262 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4013. Min Act: -0.1700
Data Index: 5235701 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.4013. Min Act: -0.1700
Data Index: 6613204 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.2763. Min Act: -0.1700
Data Index: 390725 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.3388. Min Act: -0.1700
Data Index: 3338511 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.3388. Min Act: -0.1700
Data Index: 4218306 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7763. Min Range: -8.7763
Max Act: 8.3388. Min Act: -0.1700
Data Index: 7603538 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19