Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 603 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.4683. Min Act: -0.1700
Data Index: 1846040 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.3745. Min Act: -0.1700
Data Index: 5566244 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.1245. Min Act: -0.1700
Data Index: 3954063 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.0620. Min Act: -0.1700
Data Index: 6339017 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9683. Min Act: -0.1700
Data Index: 122259 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9058. Min Act: -0.1700
Data Index: 6917324 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8745. Min Act: -0.1700
Data Index: 3803606 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8745. Min Act: -0.1700
Data Index: 6496186 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8745. Min Act: -0.1700
Data Index: 5781134 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8433. Min Act: -0.1700
Data Index: 6539030 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8433. Min Act: -0.1700
Data Index: 386419 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8433. Min Act: -0.1700
Data Index: 6211851 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.7808. Min Act: -0.1700
Data Index: 699102 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.7495. Min Act: -0.1700
Data Index: 1396930 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.7183. Min Act: -0.1700
Data Index: 6326274 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.6870. Min Act: -0.1700
Data Index: 3577409 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.7495. Min Act: -0.1700
Data Index: 6733879 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.6870. Min Act: -0.1700
Data Index: 5732341 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.6870. Min Act: -0.1700
Data Index: 2400567 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.6870. Min Act: -0.1700
Data Index: 156971 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19