Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5934. Min Range: -10.5934
Max Act: 10.5934. Min Act: -0.1700
Data Index: 842850 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5934. Min Range: -10.5934
Max Act: 10.4059. Min Act: -0.1700
Data Index: 5705935 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5934. Min Range: -10.5934
Max Act: 10.1559. Min Act: -0.1700
Data Index: 8068309 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.8434. Min Act: -0.1700
Data Index: 7484022 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.7809. Min Act: -0.1700
Data Index: 1113089 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.4684. Min Act: -0.1700
Data Index: 2758592 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.5309. Min Act: -0.1700
Data Index: 8023050 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.4059. Min Act: -0.1700
Data Index: 2455048 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.2809. Min Act: -0.1700
Data Index: 1880789 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.2809. Min Act: -0.1700
Data Index: 316540 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.2184. Min Act: -0.1700
Data Index: 7020655 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.1559. Min Act: -0.1700
Data Index: 6694844 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.1559. Min Act: -0.1700
Data Index: 3755519 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.0934. Min Act: -0.1700
Data Index: 3918265 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5934. Min Range: -10.5934
Max Act: 9.0934. Min Act: -0.1700
Data Index: 1677365 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5934. Min Range: -10.5934
Max Act: 8.9684. Min Act: -0.1700
Data Index: 426303 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5934. Min Range: -10.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 3139611 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5934. Min Range: -10.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 3308072 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5934. Min Range: -10.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 5396423 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5934. Min Range: -10.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 7186035 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19