Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.3181. Min Act: -0.1700
Data Index: 5205404 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.1931. Min Act: -0.1700
Data Index: 3824789 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0994. Min Act: -0.1700
Data Index: 2225895 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0681. Min Act: -0.1700
Data Index: 285470 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0681. Min Act: -0.1700
Data Index: 7869882 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0681. Min Act: -0.1700
Data Index: 1770636 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0369. Min Act: -0.1700
Data Index: 5224731 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0369. Min Act: -0.1700
Data Index: 2068064 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0369. Min Act: -0.1700
Data Index: 6887250 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0369. Min Act: -0.1700
Data Index: 1207873 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0056. Min Act: -0.1700
Data Index: 2230635 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3181. Min Range: -5.3181
Max Act: 5.0056. Min Act: -0.1700
Data Index: 1311780 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3181. Min Range: -5.3181
Max Act: 4.9744. Min Act: -0.1700
Data Index: 6812247 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3181. Min Range: -5.3181
Max Act: 4.9744. Min Act: -0.1700
Data Index: 8298305 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3181. Min Range: -5.3181
Max Act: 4.9744. Min Act: -0.1700
Data Index: 8006709 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3181. Min Range: -5.3181
Max Act: 4.9744. Min Act: -0.1700
Data Index: 2785109 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3181. Min Range: -5.3181
Max Act: 4.9431. Min Act: -0.1700
Data Index: 6143292 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3181. Min Range: -5.3181
Max Act: 4.9431. Min Act: -0.1700
Data Index: 947808 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3181. Min Range: -5.3181
Max Act: 4.9431. Min Act: -0.1700
Data Index: 2584961 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3181. Min Range: -5.3181
Max Act: 4.9431. Min Act: -0.1700
Data Index: 6464292 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19