Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 73 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2206. Min Range: -9.2206
Max Act: 9.2206. Min Act: -0.1700
Data Index: 1168012 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2206. Min Range: -9.2206
Max Act: 9.1581. Min Act: -0.1700
Data Index: 6897734 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2206. Min Range: -9.2206
Max Act: 9.0956. Min Act: -0.1700
Data Index: 2211765 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.9706. Min Act: -0.1700
Data Index: 813769 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.9706. Min Act: -0.1700
Data Index: 35351 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.8456. Min Act: -0.1700
Data Index: 4333056 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.8456. Min Act: -0.1700
Data Index: 2694307 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.8456. Min Act: -0.1700
Data Index: 431717 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.8456. Min Act: -0.1700
Data Index: 2510659 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.8456. Min Act: -0.1700
Data Index: 3716884 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.7831. Min Act: -0.1700
Data Index: 4432367 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.7831. Min Act: -0.1700
Data Index: 2510658 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.7206. Min Act: -0.1700
Data Index: 3407785 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.7206. Min Act: -0.1700
Data Index: 5984893 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.7206. Min Act: -0.1700
Data Index: 3767651 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.7206. Min Act: -0.1700
Data Index: 739897 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.7206. Min Act: -0.1700
Data Index: 535425 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.7206. Min Act: -0.1700
Data Index: 2706521 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.6581. Min Act: -0.1700
Data Index: 6293387 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2206. Min Range: -9.2206
Max Act: 8.6581. Min Act: -0.1700
Data Index: 6072614 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19