Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.8513. Min Act: -0.1700
Data Index: 4665304 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.6950. Min Act: -0.1700
Data Index: 4198416 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.6950. Min Act: -0.1700
Data Index: 3567897 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.6325. Min Act: -0.1700
Data Index: 8680871 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.6325. Min Act: -0.1700
Data Index: 6795082 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.5388. Min Act: -0.1700
Data Index: 3148349 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.5388. Min Act: -0.1700
Data Index: 4665306 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.5388. Min Act: -0.1700
Data Index: 6889442 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.5075. Min Act: -0.1700
Data Index: 802358 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4762. Min Act: -0.1700
Data Index: 3072521 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4762. Min Act: -0.1700
Data Index: 7093201 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4450. Min Act: -0.1700
Data Index: 40417 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4450. Min Act: -0.1700
Data Index: 2589630 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4450. Min Act: -0.1700
Data Index: 2577564 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4450. Min Act: -0.1700
Data Index: 2561374 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4762. Min Act: -0.1700
Data Index: 6726643 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4450. Min Act: -0.1700
Data Index: 3251084 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4137. Min Act: -0.1700
Data Index: 4665305 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4137. Min Act: -0.1700
Data Index: 1604559 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4137. Min Act: -0.1700
Data Index: 576129 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19