Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0161. Min Range: -6.0161
Max Act: 6.0161. Min Act: -0.1700
Data Index: 2807744 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0161. Min Range: -6.0161
Max Act: 6.0161. Min Act: -0.1700
Data Index: 6502387 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.9536. Min Act: -0.1700
Data Index: 7525028 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.9223. Min Act: -0.1700
Data Index: 983074 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.9536. Min Act: -0.1700
Data Index: 864914 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.9223. Min Act: -0.1700
Data Index: 1302420 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8598. Min Act: -0.1700
Data Index: 5122304 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8911. Min Act: -0.1700
Data Index: 6107991 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8911. Min Act: -0.1700
Data Index: 6757884 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8598. Min Act: -0.1700
Data Index: 7247251 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8598. Min Act: -0.1700
Data Index: 5932982 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8598. Min Act: -0.1700
Data Index: 8253923 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8598. Min Act: -0.1700
Data Index: 557244 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8286. Min Act: -0.1700
Data Index: 6793473 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8286. Min Act: -0.1700
Data Index: 7306940 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8286. Min Act: -0.1700
Data Index: 6773409 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8286. Min Act: -0.1700
Data Index: 8656301 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.8286. Min Act: -0.1700
Data Index: 303185 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.7973. Min Act: -0.1700
Data Index: 6334005 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0161. Min Range: -6.0161
Max Act: 5.7973. Min Act: -0.1700
Data Index: 1898031 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19