Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 257 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1712. Min Range: -6.1712
Max Act: 6.1712. Min Act: -0.1700
Data Index: 7533337 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1712. Min Range: -6.1712
Max Act: 6.1400. Min Act: -0.1700
Data Index: 4685327 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1712. Min Range: -6.1712
Max Act: 6.0462. Min Act: -0.1700
Data Index: 6162755 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1712. Min Range: -6.1712
Max Act: 6.0150. Min Act: -0.1700
Data Index: 7200408 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1712. Min Range: -6.1712
Max Act: 6.0150. Min Act: -0.1700
Data Index: 5954516 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.9837. Min Act: -0.1700
Data Index: 4059166 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.9525. Min Act: -0.1700
Data Index: 7533352 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.9525. Min Act: -0.1700
Data Index: 3977824 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.9525. Min Act: -0.1700
Data Index: 242928 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.9212. Min Act: -0.1700
Data Index: 526129 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8900. Min Act: -0.1700
Data Index: 3315742 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.9212. Min Act: -0.1700
Data Index: 5398969 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8900. Min Act: -0.1700
Data Index: 7665366 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8900. Min Act: -0.1700
Data Index: 6662808 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8900. Min Act: -0.1700
Data Index: 8554114 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8900. Min Act: -0.1700
Data Index: 2111322 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8900. Min Act: -0.1700
Data Index: 2604950 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8900. Min Act: -0.1700
Data Index: 884479 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8587. Min Act: -0.1700
Data Index: 6906621 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1712. Min Range: -6.1712
Max Act: 5.8275. Min Act: -0.1700
Data Index: 7200407 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19