Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1232 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.2691. Min Act: -0.1700
Data Index: 8193908 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.2378. Min Act: -0.1700
Data Index: 4611854 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.2378. Min Act: -0.1700
Data Index: 5382183 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.1128. Min Act: -0.1700
Data Index: 7965756 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.1441. Min Act: -0.1700
Data Index: 5417507 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.1128. Min Act: -0.1700
Data Index: 7678864 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.1753. Min Act: -0.1700
Data Index: 7387995 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.1128. Min Act: -0.1700
Data Index: 5802150 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.0816. Min Act: -0.1700
Data Index: 5490084 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.0503. Min Act: -0.1700
Data Index: 8618486 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.0503. Min Act: -0.1700
Data Index: 3939340 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2691. Min Range: -5.2691
Max Act: 5.0191. Min Act: -0.1700
Data Index: 4138791 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2691. Min Range: -5.2691
Max Act: 4.9878. Min Act: -0.1700
Data Index: 251029 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2691. Min Range: -5.2691
Max Act: 4.9878. Min Act: -0.1700
Data Index: 8113561 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2691. Min Range: -5.2691
Max Act: 4.9878. Min Act: -0.1700
Data Index: 1406754 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2691. Min Range: -5.2691
Max Act: 4.9878. Min Act: -0.1700
Data Index: 3229875 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2691. Min Range: -5.2691
Max Act: 4.9878. Min Act: -0.1700
Data Index: 2516001 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2691. Min Range: -5.2691
Max Act: 4.9878. Min Act: -0.1700
Data Index: 276547 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2691. Min Range: -5.2691
Max Act: 4.9566. Min Act: -0.1700
Data Index: 4495910 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2691. Min Range: -5.2691
Max Act: 4.9566. Min Act: -0.1700
Data Index: 4542480 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19