Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1543. Min Range: -7.1543
Max Act: 7.1543. Min Act: -0.1700
Data Index: 1146348 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.8105. Min Act: -0.1700
Data Index: 3380194 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.7480. Min Act: -0.1700
Data Index: 8830293 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.6855. Min Act: -0.1700
Data Index: 632240 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.6543. Min Act: -0.1700
Data Index: 38753 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.6543. Min Act: -0.1700
Data Index: 2801510 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.6230. Min Act: -0.1700
Data Index: 8457561 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.5918. Min Act: -0.1700
Data Index: 2100281 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.5918. Min Act: -0.1700
Data Index: 3176390 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.5605. Min Act: -0.1700
Data Index: 5300051 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.5605. Min Act: -0.1700
Data Index: 5496240 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.5293. Min Act: -0.1700
Data Index: 4942827 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.4980. Min Act: -0.1700
Data Index: 7776351 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.4980. Min Act: -0.1700
Data Index: 345874 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.4980. Min Act: -0.1700
Data Index: 3771698 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.4668. Min Act: -0.1700
Data Index: 7674826 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.4668. Min Act: -0.1700
Data Index: 1367632 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.4668. Min Act: -0.1700
Data Index: 578354 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.4668. Min Act: -0.1700
Data Index: 5570272 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1543. Min Range: -7.1543
Max Act: 6.4668. Min Act: -0.1700
Data Index: 6341948 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19