Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.5485. Min Act: -0.1700
Data Index: 8460128 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.3610. Min Act: -0.1700
Data Index: 7470071 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.2673. Min Act: -0.1700
Data Index: 3797185 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5485. Min Range: -7.5485
Max Act: 7.1735. Min Act: -0.1700
Data Index: 2653553 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.9548. Min Act: -0.1700
Data Index: 2711497 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.8923. Min Act: -0.1700
Data Index: 4395676 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.8923. Min Act: -0.1700
Data Index: 3647625 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.8298. Min Act: -0.1700
Data Index: 1492302 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.8610. Min Act: -0.1700
Data Index: 3941510 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.8298. Min Act: -0.1700
Data Index: 6517995 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.8298. Min Act: -0.1700
Data Index: 43598 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.7985. Min Act: -0.1700
Data Index: 7526538 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.7673. Min Act: -0.1700
Data Index: 1478095 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.7673. Min Act: -0.1700
Data Index: 1480040 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.7048. Min Act: -0.1700
Data Index: 3639630 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.7048. Min Act: -0.1700
Data Index: 5316534 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.7048. Min Act: -0.1700
Data Index: 7706653 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.7048. Min Act: -0.1700
Data Index: 2834154 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.6423. Min Act: -0.1700
Data Index: 6806068 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5485. Min Range: -7.5485
Max Act: 6.6735. Min Act: -0.1700
Data Index: 8444040 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19