Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.9480. Min Act: -0.1700
Data Index: 177105 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.8543. Min Act: -0.1700
Data Index: 1477261 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.8230. Min Act: -0.1700
Data Index: 4213584 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.7918. Min Act: -0.1700
Data Index: 4508810 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.7605. Min Act: -0.1700
Data Index: 4724429 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.7293. Min Act: -0.1700
Data Index: 2396596 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.7293. Min Act: -0.1700
Data Index: 5959996 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.6980. Min Act: -0.1700
Data Index: 7396712 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.6668. Min Act: -0.1700
Data Index: 3434835 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.6668. Min Act: -0.1700
Data Index: 2396597 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.6355. Min Act: -0.1700
Data Index: 2426075 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.6043. Min Act: -0.1700
Data Index: 3566730 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.6043. Min Act: -0.1700
Data Index: 936234 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.6043. Min Act: -0.1700
Data Index: 5447999 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.5730. Min Act: -0.1700
Data Index: 8304638 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.5730. Min Act: -0.1700
Data Index: 6790796 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.5730. Min Act: -0.1700
Data Index: 6330610 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.5418. Min Act: -0.1700
Data Index: 1211310 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.5418. Min Act: -0.1700
Data Index: 791552 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9480. Min Range: -4.9480
Max Act: 4.5730. Min Act: -0.1700
Data Index: 5577185 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19