Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4254 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.9693. Min Act: -0.1700
Data Index: 317233 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.7193. Min Act: -0.1700
Data Index: 7109019 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.7193. Min Act: -0.1700
Data Index: 7860255 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.4693. Min Act: -0.1700
Data Index: 6368378 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.4693. Min Act: -0.1700
Data Index: 7842921 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.4380. Min Act: -0.1700
Data Index: 8220594 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.3443. Min Act: -0.1700
Data Index: 5643996 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.3443. Min Act: -0.1700
Data Index: 1824673 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.2818. Min Act: -0.1700
Data Index: 7690414 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.2505. Min Act: -0.1700
Data Index: 4245063 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.2505. Min Act: -0.1700
Data Index: 8496533 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.1255. Min Act: -0.1700
Data Index: 1112414 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.1255. Min Act: -0.1700
Data Index: 3459225 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.1255. Min Act: -0.1700
Data Index: 2906488 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.0943. Min Act: -0.1700
Data Index: 5828658 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.1255. Min Act: -0.1700
Data Index: 5120577 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.1255. Min Act: -0.1700
Data Index: 8252960 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.1255. Min Act: -0.1700
Data Index: 6805752 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.1255. Min Act: -0.1700
Data Index: 1289822 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9693. Min Range: -7.9693
Max Act: 7.0943. Min Act: -0.1700
Data Index: 2146451 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19