Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 524 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.4552. Min Act: -0.1700
Data Index: 6296602 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.4552. Min Act: -0.1700
Data Index: 4516167 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.3615. Min Act: -0.1700
Data Index: 4081175 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.3302. Min Act: -0.1700
Data Index: 2010925 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.3302. Min Act: -0.1700
Data Index: 1377224 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.3302. Min Act: -0.1700
Data Index: 2267207 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2990. Min Act: -0.1700
Data Index: 8429555 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2677. Min Act: -0.1700
Data Index: 5089400 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2677. Min Act: -0.1700
Data Index: 2392956 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2677. Min Act: -0.1700
Data Index: 3415578 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2677. Min Act: -0.1700
Data Index: 6059861 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.3302. Min Act: -0.1700
Data Index: 2562637 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2365. Min Act: -0.1700
Data Index: 1179065 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2052. Min Act: -0.1700
Data Index: 3106218 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2677. Min Act: -0.1700
Data Index: 5577053 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2365. Min Act: -0.1700
Data Index: 6072431 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2677. Min Act: -0.1700
Data Index: 1089939 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2052. Min Act: -0.1700
Data Index: 375069 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2052. Min Act: -0.1700
Data Index: 4509143 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4552. Min Range: -5.4552
Max Act: 5.2052. Min Act: -0.1700
Data Index: 167940 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19