Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2086. Min Range: -4.2086
Max Act: 4.2086. Min Act: -0.1700
Data Index: 4056988 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2086. Min Range: -4.2086
Max Act: 4.1461. Min Act: -0.1700
Data Index: 4222984 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2086. Min Range: -4.2086
Max Act: 4.1461. Min Act: -0.1700
Data Index: 5781550 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2086. Min Range: -4.2086
Max Act: 4.1461. Min Act: -0.1700
Data Index: 6950213 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2086. Min Range: -4.2086
Max Act: 4.0211. Min Act: -0.1700
Data Index: 2750026 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.9273. Min Act: -0.1700
Data Index: 8661616 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.9586. Min Act: -0.1700
Data Index: 7577431 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.9273. Min Act: -0.1700
Data Index: 3374329 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.9273. Min Act: -0.1700
Data Index: 7605344 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8960. Min Act: -0.1700
Data Index: 4772405 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8960. Min Act: -0.1700
Data Index: 3592080 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8648. Min Act: -0.1700
Data Index: 2815382 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8648. Min Act: -0.1700
Data Index: 5375631 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8648. Min Act: -0.1700
Data Index: 8466290 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8648. Min Act: -0.1700
Data Index: 6361602 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8648. Min Act: -0.1700
Data Index: 219849 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8648. Min Act: -0.1700
Data Index: 4435307 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8648. Min Act: -0.1700
Data Index: 2895564 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8335. Min Act: -0.1700
Data Index: 7520316 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2086. Min Range: -4.2086
Max Act: 3.8335. Min Act: -0.1700
Data Index: 6119036 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19