Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3176 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2686. Min Range: -2.2686
Max Act: 2.2686. Min Act: -0.1700
Data Index: 7038502 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2686. Min Range: -2.2686
Max Act: 2.0689. Min Act: -0.1700
Data Index: 5306814 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2686. Min Range: -2.2686
Max Act: 2.0689. Min Act: -0.1699
Data Index: 2028691 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2686. Min Range: -2.2686
Max Act: 2.0352. Min Act: -0.1700
Data Index: 8423070 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2686. Min Range: -2.2686
Max Act: 2.0521. Min Act: -0.1699
Data Index: 2063243 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2686. Min Range: -2.2686
Max Act: 2.0184. Min Act: -0.1700
Data Index: 8382205 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2686. Min Range: -2.2686
Max Act: 2.0015. Min Act: -0.1654
Data Index: 4001699 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.9337. Min Act: -0.1700
Data Index: 222942 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8996. Min Act: -0.1700
Data Index: 7085966 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.9167. Min Act: -0.1700
Data Index: 7878758 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.9167. Min Act: -0.1700
Data Index: 186459 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.9167. Min Act: -0.1700
Data Index: 6343841 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8996. Min Act: -0.1692
Data Index: 7324915 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8826. Min Act: -0.1700
Data Index: 7981030 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8655. Min Act: -0.1699
Data Index: 4864222 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8826. Min Act: -0.1700
Data Index: 4230921 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8655. Min Act: -0.1700
Data Index: 7026862 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8655. Min Act: -0.1700
Data Index: 8337121 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8483. Min Act: -0.1700
Data Index: 1044584 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2686. Min Range: -2.2686
Max Act: 1.8312. Min Act: -0.1692
Data Index: 766584 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19