Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 903 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1132. Min Range: -6.1132
Max Act: 6.1132. Min Act: -0.1700
Data Index: 2072664 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1132. Min Range: -6.1132
Max Act: 6.1132. Min Act: -0.1700
Data Index: 4407742 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1132. Min Range: -6.1132
Max Act: 6.0507. Min Act: -0.1700
Data Index: 3811069 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1132. Min Range: -6.1132
Max Act: 6.0195. Min Act: -0.1700
Data Index: 340694 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.9882. Min Act: -0.1700
Data Index: 7907669 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1132. Min Range: -6.1132
Max Act: 6.0195. Min Act: -0.1700
Data Index: 7328566 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.9882. Min Act: -0.1700
Data Index: 641881 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.9570. Min Act: -0.1700
Data Index: 4023609 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.9570. Min Act: -0.1700
Data Index: 1195524 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.9570. Min Act: -0.1700
Data Index: 6293201 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.9257. Min Act: -0.1700
Data Index: 7595287 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8945. Min Act: -0.1700
Data Index: 7426939 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8945. Min Act: -0.1700
Data Index: 2618473 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8945. Min Act: -0.1700
Data Index: 633267 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8945. Min Act: -0.1700
Data Index: 4857337 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8632. Min Act: -0.1700
Data Index: 761666 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8320. Min Act: -0.1700
Data Index: 5824759 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8632. Min Act: -0.1700
Data Index: 607002 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8945. Min Act: -0.1700
Data Index: 312193 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1132. Min Range: -6.1132
Max Act: 5.8632. Min Act: -0.1700
Data Index: 4498309 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19