Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.3483. Min Act: -0.1700
Data Index: 1974078 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.3171. Min Act: -0.1700
Data Index: 8517671 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.3171. Min Act: -0.1700
Data Index: 3360056 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.1921. Min Act: -0.1700
Data Index: 8347432 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.1296. Min Act: -0.1700
Data Index: 6846656 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0983. Min Act: -0.1700
Data Index: 470101 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.1296. Min Act: -0.1700
Data Index: 7587754 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0983. Min Act: -0.1700
Data Index: 3746456 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0983. Min Act: -0.1700
Data Index: 8786059 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0671. Min Act: -0.1700
Data Index: 6779257 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0671. Min Act: -0.1700
Data Index: 3656805 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0671. Min Act: -0.1700
Data Index: 8517670 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0671. Min Act: -0.1700
Data Index: 3746457 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0358. Min Act: -0.1700
Data Index: 8233578 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0671. Min Act: -0.1700
Data Index: 446114 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0358. Min Act: -0.1700
Data Index: 1629871 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0046. Min Act: -0.1700
Data Index: 3113827 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0046. Min Act: -0.1700
Data Index: 1145623 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0046. Min Act: -0.1700
Data Index: 1280610 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3483. Min Range: -5.3483
Max Act: 5.0046. Min Act: -0.1700
Data Index: 6838981 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19