Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.7152. Min Act: -0.1700
Data Index: 5495763 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.4652. Min Act: -0.1700
Data Index: 5288197 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.4027. Min Act: -0.1700
Data Index: 2760001 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.2464. Min Act: -0.1700
Data Index: 290210 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.2152. Min Act: -0.1700
Data Index: 7510698 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.2464. Min Act: -0.1700
Data Index: 4211601 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.2152. Min Act: -0.1700
Data Index: 1379212 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.1527. Min Act: -0.1700
Data Index: 3875499 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.1527. Min Act: -0.1700
Data Index: 8567127 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.0589. Min Act: -0.1700
Data Index: 3947196 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.1214. Min Act: -0.1700
Data Index: 6847200 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.0589. Min Act: -0.1700
Data Index: 4848737 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.0902. Min Act: -0.1700
Data Index: 5283821 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.0589. Min Act: -0.1700
Data Index: 215084 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.0589. Min Act: -0.1700
Data Index: 643363 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7152. Min Range: -7.7152
Max Act: 7.0277. Min Act: -0.1700
Data Index: 4848733 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7152. Min Range: -7.7152
Max Act: 6.9964. Min Act: -0.1700
Data Index: 6582543 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7152. Min Range: -7.7152
Max Act: 6.9652. Min Act: -0.1700
Data Index: 7271890 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7152. Min Range: -7.7152
Max Act: 6.9652. Min Act: -0.1700
Data Index: 5067935 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7152. Min Range: -7.7152
Max Act: 6.9964. Min Act: -0.1700
Data Index: 6251530 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19