Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1318. Min Act: -0.1700
Data Index: 4324699 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 4805920 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1005. Min Act: -0.1700
Data Index: 3118647 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 3116446 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 3079763 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 793920 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0380. Min Act: -0.1700
Data Index: 4679787 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0068. Min Act: -0.1700
Data Index: 4700086 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0068. Min Act: -0.1700
Data Index: 1146679 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0068. Min Act: -0.1700
Data Index: 3182148 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9755. Min Act: -0.1700
Data Index: 4700099 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9755. Min Act: -0.1700
Data Index: 132148 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9443. Min Act: -0.1700
Data Index: 1231019 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9443. Min Act: -0.1700
Data Index: 4429293 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9443. Min Act: -0.1700
Data Index: 116262 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9443. Min Act: -0.1700
Data Index: 5771182 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9443. Min Act: -0.1700
Data Index: 650231 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9130. Min Act: -0.1700
Data Index: 484907 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9130. Min Act: -0.1700
Data Index: 1285109 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9130. Min Act: -0.1700
Data Index: 114924 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19