Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0043. Min Range: -1.0043
Max Act: 1.0043. Min Act: -0.1623
Data Index: 541409 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.9696. Min Act: -0.1267
Data Index: 5655781 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.9179. Min Act: -0.1700
Data Index: 7633555 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.8837. Min Act: -0.1699
Data Index: 6627564 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.8837. Min Act: -0.1641
Data Index: 8225333 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.8497. Min Act: -0.1441
Data Index: 3230471 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.8328. Min Act: -0.1699
Data Index: 2110601 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.8328. Min Act: -0.1675
Data Index: 4553003 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.8159. Min Act: -0.1386
Data Index: 1287689 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7824. Min Act: -0.1676
Data Index: 4206209 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7824. Min Act: -0.1469
Data Index: 1071147 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7657. Min Act: -0.1660
Data Index: 1624494 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7657. Min Act: -0.1670
Data Index: 4680277 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7657. Min Act: -0.1541
Data Index: 330389 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7491. Min Act: -0.1699
Data Index: 1048849 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7657. Min Act: -0.1089
Data Index: 8382309 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7657. Min Act: -0.1169
Data Index: 622769 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7657. Min Act: -0.1450
Data Index: 1606197 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7491. Min Act: -0.1700
Data Index: 381831 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0043. Min Range: -1.0043
Max Act: 0.7491. Min Act: -0.1653
Data Index: 2934578 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19