Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1397 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.7688. Min Act: -0.1700
Data Index: 8197053 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.6247. Min Act: -0.1700
Data Index: 6072748 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5925. Min Act: -0.1700
Data Index: 3147460 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5764. Min Act: -0.1700
Data Index: 1107220 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5925. Min Act: -0.1700
Data Index: 2874895 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5764. Min Act: -0.1700
Data Index: 7085841 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5603. Min Act: -0.1700
Data Index: 7790066 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5764. Min Act: -0.1700
Data Index: 7461793 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5280. Min Act: -0.1700
Data Index: 163157 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5441. Min Act: -0.1700
Data Index: 163154 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5118. Min Act: -0.1700
Data Index: 8229682 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.4956. Min Act: -0.1700
Data Index: 7008809 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5118. Min Act: -0.1700
Data Index: 3087932 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.5118. Min Act: -0.1700
Data Index: 5540476 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.4956. Min Act: -0.1700
Data Index: 4462712 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.4794. Min Act: -0.1700
Data Index: 7790091 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.4794. Min Act: -0.1700
Data Index: 7758546 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.4794. Min Act: -0.1699
Data Index: 5979191 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.4632. Min Act: -0.1700
Data Index: 7790067 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7688. Min Range: -2.7688
Max Act: 2.4632. Min Act: -0.1700
Data Index: 4397639 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19