Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 216 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.9382. Min Act: -0.1700
Data Index: 1393887 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.6882. Min Act: -0.1700
Data Index: 5610095 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.6257. Min Act: -0.1700
Data Index: 1208298 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.4382. Min Act: -0.1700
Data Index: 194220 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.4382. Min Act: -0.1700
Data Index: 3474196 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.3757. Min Act: -0.1700
Data Index: 2003968 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.1257. Min Act: -0.1700
Data Index: 2830958 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.1257. Min Act: -0.1700
Data Index: 3242600 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.0007. Min Act: -0.1700
Data Index: 3680464 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.0007. Min Act: -0.1700
Data Index: 6327357 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.0007. Min Act: -0.1700
Data Index: 4457458 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.9382. Min Range: -14.9382
Max Act: 13.9382. Min Act: -0.1700
Data Index: 3059458 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.0007. Min Act: -0.1700
Data Index: 7279183 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.9382. Min Range: -14.9382
Max Act: 14.0007. Min Act: -0.1700
Data Index: 3736735 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.9382. Min Range: -14.9382
Max Act: 13.8757. Min Act: -0.1700
Data Index: 7648964 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.9382. Min Range: -14.9382
Max Act: 13.8132. Min Act: -0.1700
Data Index: 3975057 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.9382. Min Range: -14.9382
Max Act: 13.8132. Min Act: -0.1700
Data Index: 482358 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.9382. Min Range: -14.9382
Max Act: 13.8132. Min Act: -0.1700
Data Index: 1137358 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.9382. Min Range: -14.9382
Max Act: 13.7507. Min Act: -0.1700
Data Index: 7812052 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.9382. Min Range: -14.9382
Max Act: 13.6882. Min Act: -0.1700
Data Index: 5150990 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19