Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4811 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1143. Min Range: -6.1143
Max Act: 6.1143. Min Act: -0.1700
Data Index: 5028892 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1143. Min Range: -6.1143
Max Act: 6.0518. Min Act: -0.1700
Data Index: 3338613 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.9893. Min Act: -0.1700
Data Index: 8783828 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.9581. Min Act: -0.1700
Data Index: 8321509 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.8643. Min Act: -0.1700
Data Index: 8185393 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.8643. Min Act: -0.1700
Data Index: 8538674 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.8331. Min Act: -0.1700
Data Index: 257700 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.8018. Min Act: -0.1700
Data Index: 3847105 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.8018. Min Act: -0.1700
Data Index: 2638255 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.7393. Min Act: -0.1700
Data Index: 7962631 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.7706. Min Act: -0.1700
Data Index: 3398898 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.7081. Min Act: -0.1700
Data Index: 3907134 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.6768. Min Act: -0.1700
Data Index: 6376065 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.7081. Min Act: -0.1700
Data Index: 5330792 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.7081. Min Act: -0.1700
Data Index: 3560273 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.7081. Min Act: -0.1700
Data Index: 1978489 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.7081. Min Act: -0.1700
Data Index: 8639783 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.6456. Min Act: -0.1700
Data Index: 4126310 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.6143. Min Act: -0.1700
Data Index: 2526432 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1143. Min Range: -6.1143
Max Act: 5.6456. Min Act: -0.1700
Data Index: 5240430 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19