Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2030 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.1650. Min Act: -0.1700
Data Index: 1412298 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.1337. Min Act: -0.1700
Data Index: 3248596 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.0712. Min Act: -0.1700
Data Index: 8169642 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.0400. Min Act: -0.1700
Data Index: 1293457 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.0087. Min Act: -0.1700
Data Index: 1480510 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.0400. Min Act: -0.1700
Data Index: 8554722 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.0087. Min Act: -0.1700
Data Index: 92251 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.9775. Min Act: -0.1700
Data Index: 4428869 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.0087. Min Act: -0.1700
Data Index: 1545482 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1650. Min Range: -6.1650
Max Act: 6.0087. Min Act: -0.1700
Data Index: 3228018 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.9462. Min Act: -0.1700
Data Index: 2877638 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.9775. Min Act: -0.1700
Data Index: 6286193 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.9150. Min Act: -0.1700
Data Index: 5025381 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.8837. Min Act: -0.1700
Data Index: 247407 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.8525. Min Act: -0.1700
Data Index: 8438327 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.8837. Min Act: -0.1700
Data Index: 4677492 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.8525. Min Act: -0.1700
Data Index: 1097152 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.8525. Min Act: -0.1700
Data Index: 5107150 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.7900. Min Act: -0.1700
Data Index: 5300938 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1650. Min Range: -6.1650
Max Act: 5.8837. Min Act: -0.1700
Data Index: 304348 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19