Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2873 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.8450. Min Act: -0.1700
Data Index: 2394661 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.8450. Min Act: -0.1700
Data Index: 8064191 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.8137. Min Act: -0.1700
Data Index: 986533 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.5950. Min Act: -0.1700
Data Index: 7162461 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.5325. Min Act: -0.1700
Data Index: 1361213 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.5325. Min Act: -0.1700
Data Index: 486571 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.5012. Min Act: -0.1700
Data Index: 1599900 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.5012. Min Act: -0.1700
Data Index: 8196321 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.4700. Min Act: -0.1700
Data Index: 3814435 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.4387. Min Act: -0.1700
Data Index: 1732023 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.4075. Min Act: -0.1700
Data Index: 8302815 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.4075. Min Act: -0.1700
Data Index: 1986472 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.4075. Min Act: -0.1700
Data Index: 8680523 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.4075. Min Act: -0.1700
Data Index: 6552201 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.3762. Min Act: -0.1700
Data Index: 2724549 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.3450. Min Act: -0.1700
Data Index: 8671474 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.3450. Min Act: -0.1700
Data Index: 7421880 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.3450. Min Act: -0.1700
Data Index: 734020 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.3762. Min Act: -0.1700
Data Index: 8608131 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8450. Min Range: -4.8450
Max Act: 4.3137. Min Act: -0.1700
Data Index: 388172 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19