Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.7194. Min Act: -0.1700
Data Index: 5273803 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.5319. Min Act: -0.1700
Data Index: 2531771 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.5007. Min Act: -0.1700
Data Index: 2480716 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.5007. Min Act: -0.1700
Data Index: 8292458 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.4694. Min Act: -0.1700
Data Index: 4697275 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.4382. Min Act: -0.1700
Data Index: 7428787 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.3444. Min Act: -0.1700
Data Index: 6434347 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.3132. Min Act: -0.1700
Data Index: 4506844 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.2819. Min Act: -0.1700
Data Index: 2875078 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.2507. Min Act: -0.1700
Data Index: 173733 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.2194. Min Act: -0.1700
Data Index: 1293113 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.2194. Min Act: -0.1700
Data Index: 5187091 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.1882. Min Act: -0.1700
Data Index: 5452302 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.1569. Min Act: -0.1700
Data Index: 1302808 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.1569. Min Act: -0.1700
Data Index: 5546275 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.1257. Min Act: -0.1700
Data Index: 1740549 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.1257. Min Act: -0.1700
Data Index: 8616103 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.1257. Min Act: -0.1700
Data Index: 653937 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.1257. Min Act: -0.1700
Data Index: 7046236 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7194. Min Range: -7.7194
Max Act: 7.1257. Min Act: -0.1700
Data Index: 4995368 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19