Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0505. Min Range: -4.0505
Max Act: 4.0505. Min Act: -0.1700
Data Index: 7486444 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0505. Min Range: -4.0505
Max Act: 4.0505. Min Act: -0.1700
Data Index: 5865751 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0505. Min Range: -4.0505
Max Act: 4.0193. Min Act: -0.1700
Data Index: 7113053 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0505. Min Range: -4.0505
Max Act: 4.0193. Min Act: -0.1700
Data Index: 8265542 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.9567. Min Act: -0.1700
Data Index: 4395004 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.9255. Min Act: -0.1700
Data Index: 680905 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.9567. Min Act: -0.1700
Data Index: 5033010 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.9255. Min Act: -0.1700
Data Index: 5335175 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.9255. Min Act: -0.1700
Data Index: 2963291 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.9255. Min Act: -0.1700
Data Index: 1544463 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8629. Min Act: -0.1700
Data Index: 8158202 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8629. Min Act: -0.1700
Data Index: 3521791 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8629. Min Act: -0.1700
Data Index: 6227827 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8942. Min Act: -0.1700
Data Index: 3068222 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8629. Min Act: -0.1700
Data Index: 8155275 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8629. Min Act: -0.1700
Data Index: 497405 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8942. Min Act: -0.1700
Data Index: 2117543 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8317. Min Act: -0.1700
Data Index: 2208508 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8317. Min Act: -0.1700
Data Index: 6942090 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0505. Min Range: -4.0505
Max Act: 3.8629. Min Act: -0.1700
Data Index: 835490 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19