Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 642 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5749. Min Act: -0.1700
Data Index: 2294732 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5437. Min Act: -0.1700
Data Index: 7449649 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4499. Min Act: -0.1700
Data Index: 5003683 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3874. Min Act: -0.1700
Data Index: 5722462 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3562. Min Act: -0.1700
Data Index: 5209953 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2937. Min Act: -0.1700
Data Index: 769678 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3249. Min Act: -0.1700
Data Index: 4101245 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3249. Min Act: -0.1700
Data Index: 3490781 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2937. Min Act: -0.1700
Data Index: 7119213 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2312. Min Act: -0.1700
Data Index: 2461029 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2624. Min Act: -0.1700
Data Index: 4767187 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1999. Min Act: -0.1700
Data Index: 6245896 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1999. Min Act: -0.1700
Data Index: 3397921 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1687. Min Act: -0.1700
Data Index: 7436217 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1687. Min Act: -0.1700
Data Index: 1887525 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1374. Min Act: -0.1700
Data Index: 205478 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1062. Min Act: -0.1700
Data Index: 5792671 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1374. Min Act: -0.1700
Data Index: 1420006 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1374. Min Act: -0.1700
Data Index: 6601309 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1374. Min Act: -0.1700
Data Index: 1556541 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19