Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.5507. Min Act: -0.1700
Data Index: 2740672 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.4257. Min Act: -0.1700
Data Index: 357562 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.3632. Min Act: -0.1700
Data Index: 4453788 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.3007. Min Act: -0.1700
Data Index: 4685629 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.2695. Min Act: -0.1700
Data Index: 226359 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.2382. Min Act: -0.1700
Data Index: 2421692 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.2070. Min Act: -0.1700
Data Index: 8285288 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.2070. Min Act: -0.1700
Data Index: 4833129 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.2070. Min Act: -0.1700
Data Index: 2796623 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.1757. Min Act: -0.1700
Data Index: 7405618 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.1757. Min Act: -0.1700
Data Index: 8160375 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.1757. Min Act: -0.1700
Data Index: 5232978 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.1757. Min Act: -0.1700
Data Index: 1674447 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.1445. Min Act: -0.1700
Data Index: 3070851 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.1445. Min Act: -0.1700
Data Index: 6525470 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.0820. Min Act: -0.1700
Data Index: 8160374 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.0820. Min Act: -0.1700
Data Index: 7109929 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.0820. Min Act: -0.1700
Data Index: 4495935 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.0507. Min Act: -0.1700
Data Index: 2616958 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5507. Min Range: -7.5507
Max Act: 7.0507. Min Act: -0.1700
Data Index: 3836491 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19