Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4939 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.3549. Min Act: -0.1700
Data Index: 3935416 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.3393. Min Act: -0.1700
Data Index: 3691482 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.3236. Min Act: -0.1700
Data Index: 3287808 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2922. Min Act: -0.1700
Data Index: 8109871 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2922. Min Act: -0.1700
Data Index: 1198845 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2765. Min Act: -0.1700
Data Index: 1100960 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2765. Min Act: -0.1700
Data Index: 7355385 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2608. Min Act: -0.1700
Data Index: 1428963 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2608. Min Act: -0.1700
Data Index: 115382 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2608. Min Act: -0.1700
Data Index: 4467377 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2450. Min Act: -0.1700
Data Index: 4415298 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.2293. Min Act: -0.1700
Data Index: 8439780 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.1822. Min Act: -0.1700
Data Index: 3287798 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.1822. Min Act: -0.1700
Data Index: 4243289 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.1822. Min Act: -0.1700
Data Index: 6036536 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.1822. Min Act: -0.1700
Data Index: 2025564 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.1664. Min Act: -0.1700
Data Index: 6116114 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.1664. Min Act: -0.1700
Data Index: 115380 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.1664. Min Act: -0.1700
Data Index: 8484681 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3549. Min Range: -3.3549
Max Act: 3.1664. Min Act: -0.1700
Data Index: 115381 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19