Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4267 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.8869. Min Act: -0.1700
Data Index: 34970 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2306. Min Act: -0.1700
Data Index: 8761054 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2306. Min Act: -0.1700
Data Index: 4979807 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2306. Min Act: -0.1700
Data Index: 3044647 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1681. Min Act: -0.1699
Data Index: 4767627 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1994. Min Act: -0.1700
Data Index: 6482130 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2306. Min Act: -0.1700
Data Index: 2253656 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1369. Min Act: -0.1700
Data Index: 5356291 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1056. Min Act: -0.1700
Data Index: 3655881 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1369. Min Act: -0.1700
Data Index: 4864593 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1056. Min Act: -0.1700
Data Index: 2801033 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5325654 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.0744. Min Act: -0.1700
Data Index: 3219968 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.1056. Min Act: -0.1700
Data Index: 1329898 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.0431. Min Act: -0.1700
Data Index: 5821716 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.0431. Min Act: -0.1700
Data Index: 707632 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.0119. Min Act: -0.1700
Data Index: 1296959 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8869. Min Range: -6.8869
Max Act: 5.9806. Min Act: -0.1700
Data Index: 3692597 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8869. Min Range: -6.8869
Max Act: 5.9806. Min Act: -0.1700
Data Index: 4914236 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8869. Min Range: -6.8869
Max Act: 5.9494. Min Act: -0.1700
Data Index: 5293766 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19