Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.6889. Min Act: -0.1700
Data Index: 8435652 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.6577. Min Act: -0.1700
Data Index: 5877448 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.6577. Min Act: -0.1700
Data Index: 4597753 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.6264. Min Act: -0.1700
Data Index: 6122925 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.5639. Min Act: -0.1700
Data Index: 7347259 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.5639. Min Act: -0.1700
Data Index: 6147307 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.5639. Min Act: -0.1700
Data Index: 7259271 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.5639. Min Act: -0.1700
Data Index: 2331892 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.5639. Min Act: -0.1700
Data Index: 7832159 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.5014. Min Act: -0.1700
Data Index: 1931691 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.5327. Min Act: -0.1700
Data Index: 4054780 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.4077. Min Act: -0.1700
Data Index: 1396287 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.3764. Min Act: -0.1700
Data Index: 4698441 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.3764. Min Act: -0.1700
Data Index: 3753884 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.3452. Min Act: -0.1700
Data Index: 1771133 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.3452. Min Act: -0.1700
Data Index: 6727526 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.3764. Min Act: -0.1700
Data Index: 7784877 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.3139. Min Act: -0.1700
Data Index: 7031670 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.3139. Min Act: -0.1700
Data Index: 4182262 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6889. Min Range: -4.6889
Max Act: 4.3139. Min Act: -0.1700
Data Index: 2952269 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19