Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5752 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.7445. Min Act: -0.1700
Data Index: 6732164 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.6195. Min Act: -0.1700
Data Index: 6004008 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.5883. Min Act: -0.1700
Data Index: 7695407 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.5570. Min Act: -0.1700
Data Index: 6296654 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.4945. Min Act: -0.1700
Data Index: 1025335 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.4320. Min Act: -0.1700
Data Index: 7168149 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.4008. Min Act: -0.1700
Data Index: 1995109 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3695. Min Act: -0.1700
Data Index: 4495043 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3695. Min Act: -0.1700
Data Index: 6258951 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3695. Min Act: -0.1700
Data Index: 348497 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3695. Min Act: -0.1700
Data Index: 2898774 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3383. Min Act: -0.1700
Data Index: 914923 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3383. Min Act: -0.1700
Data Index: 5844828 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3383. Min Act: -0.1700
Data Index: 702346 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3070. Min Act: -0.1700
Data Index: 4661774 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3383. Min Act: -0.1700
Data Index: 7970241 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.2758. Min Act: -0.1700
Data Index: 5450529 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3070. Min Act: -0.1700
Data Index: 4185826 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.3070. Min Act: -0.1700
Data Index: 6273243 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7445. Min Range: -5.7445
Max Act: 5.2758. Min Act: -0.1700
Data Index: 6183251 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19