Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.8593. Min Act: -0.1700
Data Index: 2310253 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.8116. Min Act: -0.1700
Data Index: 6980926 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7638. Min Act: -0.1700
Data Index: 6786028 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7638. Min Act: -0.1700
Data Index: 6078823 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7638. Min Act: -0.1700
Data Index: 6315271 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7638. Min Act: -0.1700
Data Index: 7033440 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7638. Min Act: -0.1700
Data Index: 6619445 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7479. Min Act: -0.1700
Data Index: 5879227 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7479. Min Act: -0.1700
Data Index: 705476 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7479. Min Act: -0.1700
Data Index: 8484481 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7479. Min Act: -0.1700
Data Index: 222122 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7319. Min Act: -0.1700
Data Index: 4906732 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7319. Min Act: -0.1700
Data Index: 673758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7319. Min Act: -0.1700
Data Index: 4588228 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7319. Min Act: -0.1700
Data Index: 6364813 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7319. Min Act: -0.1700
Data Index: 2249649 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7319. Min Act: -0.1700
Data Index: 272267 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7159. Min Act: -0.1700
Data Index: 1579468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7159. Min Act: -0.1700
Data Index: 2407197 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8593. Min Range: -2.8593
Max Act: 2.7159. Min Act: -0.1700
Data Index: 236766 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19