Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1062 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.9445. Min Act: -0.1700
Data Index: 5511590 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.9132. Min Act: -0.1700
Data Index: 1399674 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.7570. Min Act: -0.1700
Data Index: 3551645 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.6945. Min Act: -0.1700
Data Index: 7705081 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.5382. Min Act: -0.1700
Data Index: 5923434 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.4757. Min Act: -0.1700
Data Index: 956650 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.4757. Min Act: -0.1700
Data Index: 5724135 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.4445. Min Act: -0.1700
Data Index: 3807103 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.4445. Min Act: -0.1700
Data Index: 5651871 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.4757. Min Act: -0.1700
Data Index: 1370322 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.3820. Min Act: -0.1700
Data Index: 5975892 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.3507. Min Act: -0.1700
Data Index: 95479 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.3507. Min Act: -0.1700
Data Index: 180581 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.3507. Min Act: -0.1700
Data Index: 4452799 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.3507. Min Act: -0.1700
Data Index: 3286348 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.3507. Min Act: -0.1700
Data Index: 115828 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.3195. Min Act: -0.1700
Data Index: 2882346 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.2882. Min Act: -0.1700
Data Index: 2565664 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.2882. Min Act: -0.1700
Data Index: 7831355 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9445. Min Range: -5.9445
Max Act: 5.2570. Min Act: -0.1700
Data Index: 1689910 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19