Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4589 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4443. Min Range: -7.4443
Max Act: 7.4443. Min Act: -0.1700
Data Index: 5798803 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4443. Min Range: -7.4443
Max Act: 7.2881. Min Act: -0.1700
Data Index: 439298 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.9756. Min Act: -0.1700
Data Index: 5485712 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.9756. Min Act: -0.1700
Data Index: 6178322 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.9443. Min Act: -0.1700
Data Index: 2442244 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.9131. Min Act: -0.1700
Data Index: 263564 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.9443. Min Act: -0.1700
Data Index: 7464086 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.8818. Min Act: -0.1700
Data Index: 1420976 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.8506. Min Act: -0.1700
Data Index: 1420977 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.8193. Min Act: -0.1700
Data Index: 3069780 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.8193. Min Act: -0.1700
Data Index: 7292945 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.8193. Min Act: -0.1700
Data Index: 4577908 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.7881. Min Act: -0.1700
Data Index: 6670783 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.7568. Min Act: -0.1700
Data Index: 1420973 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.7256. Min Act: -0.1700
Data Index: 3001065 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.6943. Min Act: -0.1700
Data Index: 3521838 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.6943. Min Act: -0.1700
Data Index: 6670782 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.6631. Min Act: -0.1700
Data Index: 7269111 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.6943. Min Act: -0.1700
Data Index: 2385944 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4443. Min Range: -7.4443
Max Act: 6.6943. Min Act: -0.1700
Data Index: 4189327 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19