Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4618 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.3206. Min Act: -0.1700
Data Index: 5626524 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.2893. Min Act: -0.1700
Data Index: 6489852 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.0706. Min Act: -0.1700
Data Index: 1665205 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.0393. Min Act: -0.1700
Data Index: 1688757 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.0081. Min Act: -0.1700
Data Index: 8086150 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8831. Min Act: -0.1700
Data Index: 1060276 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8518. Min Act: -0.1700
Data Index: 4717408 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8206. Min Act: -0.1700
Data Index: 7914136 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8518. Min Act: -0.1700
Data Index: 2848588 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8206. Min Act: -0.1700
Data Index: 3574740 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8206. Min Act: -0.1700
Data Index: 8789434 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8206. Min Act: -0.1700
Data Index: 2234335 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.7581. Min Act: -0.1700
Data Index: 1540890 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.7268. Min Act: -0.1700
Data Index: 4500124 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.7268. Min Act: -0.1700
Data Index: 4023890 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.7268. Min Act: -0.1700
Data Index: 742299 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.7268. Min Act: -0.1700
Data Index: 7980375 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.7581. Min Act: -0.1700
Data Index: 5740676 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.6956. Min Act: -0.1700
Data Index: 1318501 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.6956. Min Act: -0.1700
Data Index: 2332196 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19