Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4987 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4812. Min Range: -7.4812
Max Act: 7.4812. Min Act: -0.1700
Data Index: 2833530 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4812. Min Range: -7.4812
Max Act: 7.2937. Min Act: -0.1700
Data Index: 7259228 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4812. Min Range: -7.4812
Max Act: 7.0437. Min Act: -0.1700
Data Index: 1296947 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4812. Min Range: -7.4812
Max Act: 7.0437. Min Act: -0.1700
Data Index: 399571 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4812. Min Range: -7.4812
Max Act: 7.0125. Min Act: -0.1700
Data Index: 1774890 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4812. Min Range: -7.4812
Max Act: 7.0125. Min Act: -0.1700
Data Index: 7825286 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.9500. Min Act: -0.1700
Data Index: 4458545 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.8875. Min Act: -0.1700
Data Index: 5175498 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.8562. Min Act: -0.1700
Data Index: 1834480 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7937. Min Act: -0.1700
Data Index: 1244421 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7625. Min Act: -0.1700
Data Index: 2488524 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7625. Min Act: -0.1700
Data Index: 3180212 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7312. Min Act: -0.1700
Data Index: 3254413 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7312. Min Act: -0.1700
Data Index: 5378053 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7000. Min Act: -0.1700
Data Index: 6615241 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7000. Min Act: -0.1700
Data Index: 3407131 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7000. Min Act: -0.1700
Data Index: 3119206 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.7000. Min Act: -0.1700
Data Index: 2818327 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.6687. Min Act: -0.1700
Data Index: 4862024 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4812. Min Range: -7.4812
Max Act: 6.6687. Min Act: -0.1700
Data Index: 7975962 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19