Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6146 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0682. Min Range: -6.0682
Max Act: 6.0682. Min Act: -0.1700
Data Index: 7082557 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0682. Min Range: -6.0682
Max Act: 6.0370. Min Act: -0.1700
Data Index: 3364357 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0682. Min Range: -6.0682
Max Act: 6.0057. Min Act: -0.1700
Data Index: 880642 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0682. Min Range: -6.0682
Max Act: 6.0057. Min Act: -0.1700
Data Index: 2063820 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.9120. Min Act: -0.1700
Data Index: 3007314 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.8807. Min Act: -0.1700
Data Index: 3523475 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.7870. Min Act: -0.1700
Data Index: 4200771 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.7870. Min Act: -0.1700
Data Index: 413104 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.7557. Min Act: -0.1700
Data Index: 5108317 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.6932. Min Act: -0.1700
Data Index: 4244256 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.6932. Min Act: -0.1700
Data Index: 373726 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.6932. Min Act: -0.1700
Data Index: 5493029 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.6932. Min Act: -0.1700
Data Index: 515739 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.6620. Min Act: -0.1700
Data Index: 8657284 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.6620. Min Act: -0.1700
Data Index: 3586021 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.6307. Min Act: -0.1700
Data Index: 8445399 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.5995. Min Act: -0.1700
Data Index: 4761736 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.6307. Min Act: -0.1700
Data Index: 5576510 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.5995. Min Act: -0.1700
Data Index: 3305229 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0682. Min Range: -6.0682
Max Act: 5.5995. Min Act: -0.1700
Data Index: 1492306 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19